[HN Gopher] New LLM optimization technique slashes memory costs
       ___________________________________________________________________
        
       New LLM optimization technique slashes memory costs
        
       Author : hochmartinez
       Score  : 428 points
       Date   : 2024-12-13 19:14 UTC (4 days ago)
        
 (HTM) web link (venturebeat.com)
 (TXT) w3m dump (venturebeat.com)
        
       | dboreham wrote:
       | TFP: https://arxiv.org/abs/2410.13166
        
         | vlovich123 wrote:
         | TFS: https://github.com/SakanaAI/evo-memory
        
       | vlovich123 wrote:
       | Wonder how this compares with Microsoft's HeadKV paper [1] which
       | claims a 98% percent reduction in memory while retaining 97% of
       | the performance.
       | 
       | [1] https://arxiv.org/html/2410.19258v3
        
         | benatkin wrote:
         | Seems like a different thing. That paper appears to be memory
         | reduction in caching while article appears to be memory
         | reduction in content.
        
           | vlovich123 wrote:
           | They're both exploring the same space of optimizing the
           | memory needed by the KV cache which is essentially another
           | name for the context window (no one elides the KV cache as
           | otherwise you're doing N^2 math to do attention). They're
           | exploring different approaches to achieve the same goal and
           | they may be both possible to apply simultaneously to reduce
           | the attention mechanism to almost 0 memory usage which would
           | be really cool, but I'm curious how they compare against each
           | other individually.
        
             | benatkin wrote:
             | That sounds like a stretch to me. If not, I'm impressed how
             | the articles can describe such similar things in such
             | different terms.
        
               | vlovich123 wrote:
               | The only memory mechanism within an LLM as far as I know
               | is the attention mechanism where it compares all previous
               | tokens to generate a probability distribution for the
               | next token to generate. The attention mechanism has a
               | thing called a KV cache to take the O(n^2) matrix math
               | down to O(n) by caching and reusing the results of some
               | math from previous tokens. The size of how many tokens
               | the context will cover is called the context window (e.g.
               | 128k for Llama).
               | 
               | The articles use very similar verbiage.
               | 
               | > The context window can be considered the model's
               | working memory
               | 
               | Snip
               | 
               | > Universal transformer memory optimizes prompts using
               | neural attention memory models (NAMMs), simple neural
               | networks that decide whether to "remember" or "forget"
               | each given token stored in the LLM's memory.
               | 
               | snip
               | 
               | > Meanwhile, by discarding unnecessary tokens, NAMM
               | enabled the LLM model to save up to 75% of its cache
               | memory while performing the tasks.
               | 
               | You just have to be familiar with the wording in the
               | space and read enough literature. Here's more direct
               | wording from the NAMM paper:
               | 
               | > NAMMs use evolution to optimize the performance of LMs
               | by pruning their KV cache memory. Evolved NAMMs can be
               | zero-shot transferred to other transformers, even across
               | input modalities and task domains.
               | 
               | This is all related work about shrinking the size of the
               | KV cache as the context grows both due to memory and it
               | also has a speed up effect since you're not having to
               | attend all the tokens (O(n) -> sublinear with the size of
               | the context).
               | 
               | Context is critical in the LLM answering correctly and
               | remembering all the information given to it + everything
               | it said. Typical limits for open models these days are
               | 128k but with techniques like this it could scale even
               | further allowing better performance on thing like code
               | completion.
        
               | benatkin wrote:
               | I thought the context would also have floating point
               | numbers so that tokens would be included in a more fuzzy
               | way, and that when requests are sent it would result in
               | loading slightly different tokens into the cache. Yeah my
               | understanding certainly is limited and I'd like to study
               | it more. Thanks for the response, I see more similarity
               | now.
        
               | vlovich123 wrote:
               | The word you're looking for is latent space and yes,
               | everything in the compute graph, including context cache
               | & compute is done in latent space. Literal input tokens
               | are first converted to latent space through the embedding
               | layer and literal output tokens are generated by
               | converting the last compute tensor into token
               | probabilities & taking the most probable token.
               | Everything in the middle though happens in the "floating
               | point" latent space.
               | 
               | When you hear something like "it's attending all previous
               | tokens" IMHO it's not strictly the correct explanation
               | since you're attending through latent space which doesn't
               | actually correspond 1:1 with tokens but is a
               | multidimensional representation of that token & all
               | preceding tokens as understood by _that_ attention head.
               | But conceptually it 's how it's described because the
               | size of your context goes up by 1 tensor for every token
               | you process, even though applying attention actually ends
               | up changing all tensors in the KV cache (hence self-
               | attention). Also important to note that each attention
               | head within each layer has it's own KV cache. LLMs are an
               | autoregressive family of models where the output of each
               | layer feeds into the input of the next and each layer has
               | a transformer performing attention. That's another reason
               | why it's not strictly correct to think of it as tokens
               | make up your context because there's actually many many
               | contexts within a transformer model. That's why your 128k
               | context window can be ~15 GiB for a naiive inference
               | implementation - 128k context window * 1024 *
               | 1024-element tensor * 2 bytes per tensor * 8 attention
               | heads * 8 layers (or something along those lines). And
               | that's what this work is talking about shrinking (as does
               | the HeadKV).
               | 
               | > tokens would be included in a more fuzzy way, and that
               | when requests are sent it would result in loading
               | slightly different tokens into the cache
               | 
               | The entire process of LLMs is generally actually 100%
               | deterministic based on the same inputs & given a fixed
               | seed for the RNG (modulo bugs in the inference math /
               | bugs in HW/SW for the accelerator). Some inference
               | implementations don't guarantee this property in the face
               | of concurrent requests & you can't control the seed for
               | hosted LLMs which is why it seems like random responses
               | for the same query.
        
               | benatkin wrote:
               | The KV cache feels more like a graph to me, like in the
               | RDF sense. Each parameter could be numbered and given a
               | URL it seems. I have some studying to do. I think
               | building a simple neural net and looking at raw data for
               | context in whatever LLM I'm playing with in Ollama are
               | good things to try.
        
             | oblio wrote:
             | > they may be both possible to apply simultaneously to
             | reduce the attention mechanism to almost 0 memory usage
             | which would be really cool
             | 
             | https://matt.might.net/articles/why-infinite-or-
             | guaranteed-f...
        
               | tsukikage wrote:
               | This isn't like lossless compression. Both techniques
               | involve throwing lots of information away, with the
               | justification that doing so does not significantly affect
               | the end result.
               | 
               | The extent to which using both the techniques together
               | will help will depend on how much overlap there is
               | between the information each ends up discarding.
        
               | oblio wrote:
               | My joke was more along the lines of entropy. Entropy is
               | information and you can't throw away all of it, otherwise
               | you have nothing useful left.
        
               | lxgr wrote:
               | Hence the idea to only throw away almost all of it.
        
               | vlovich123 wrote:
               | Modern LLMs are still quite inefficient in their
               | representation of information. We're at like the DEFLATE
               | era and we've still yet to invent zstd where there's only
               | marginal incremental gains; so right now there's a lot of
               | waste to prune away.
        
         | punkpeye wrote:
         | Any real-world (open-source) implementations of this?
        
       | ComputerGuru wrote:
       | This only decreases memory cost of input context window, not the
       | memory cost to load and run the models.
        
         | freehorse wrote:
         | Context window requires ram too.
        
         | ynniv wrote:
         | "Only"
        
         | keyle wrote:
         | I agree with you though, the title is misleading.
        
           | BoorishBears wrote:
           | Title is perfect. Their typical audience probably understands
           | "memory" better than "context window", but then if you've
           | actually deployed these systems it's not difficult to go the
           | other way, from "memory" to "context window" since the
           | context window specifically is known to take additional VRAM
           | over the model itself
        
         | solarkraft wrote:
         | And that's what matters the most! To me, at small model sizes
         | (1-8B), anyway. A few thousans tokens already bog my RAM down
         | quite a lot and I'd love to have more - I'd go as far as saying
         | that context greatly determines LLM capability at this point.
        
           | danielbln wrote:
           | Yes, pretraining and post-training is nice and important, but
           | in-context learning turns LLMs from toys into tools.
        
       | richwater wrote:
       | This is for inference right? Not training?
        
         | lawlessone wrote:
         | doesn't training require inference? so i guess it would help
         | there too?
        
           | fzzzy wrote:
           | Training doesn't require inference. It uses back-propagation,
           | a different algorithm.
        
             | bitvoid wrote:
             | Backpropagation happens after some number of inferences.
             | You need to infer to calculate a loss function to then
             | backprop from.
        
           | boringg wrote:
           | Yeah but training requires the larger memory deployment data
           | center infra
        
         | pizza wrote:
         | It's for KV caching. In most conversations that will mean
         | inference. But you _can_ do reinforcement learning using
         | sampled sequences, and you _could_ use KV caching to speed that
         | up too, so that would be an instance where training could get a
         | slight boost.
        
       | yishanchuan wrote:
       | interesting
        
       | lawlessone wrote:
       | So it's like a garbage collector for prompts?
        
         | cowsandmilk wrote:
         | More of lossy compression
        
           | aziaziazi wrote:
           | Does lossy means you may see previous inputs change ?!
        
             | TkTech wrote:
             | Lossy doesn't necessarily imply that it is non-
             | deterministic, just irreversible.
        
             | lxgr wrote:
             | Only the model's view, doesn't have to be yours, just like
             | you can participate in a long conversation without perfect
             | memory that might in retrospect slightly differ from a
             | recording.
        
           | verdverm wrote:
           | with the added bonus that these things are unreliable and the
           | compressor could drop important tokens
        
       | tharmas wrote:
       | Does this mean us plebs can run LLMs on gimped VRAM Nvidia lower
       | end cards?
        
         | swifthesitation wrote:
         | I don't think so. It seems to just lower the ram needed for the
         | context window. Not for loading the model on the vram.
        
       | iandanforth wrote:
       | Boringness classifier! Pretty cool because this implies the large
       | models already know what is useless and what isn't.
        
         | lxgr wrote:
         | > NAMMs are trained separately from the LLM and are combined
         | with the pre-trained model at inference time [...]
        
       | odyssey7 wrote:
       | Is it possible that after 3-4 years of performance optimizations,
       | both algorithmic and in hardware efficiency, it will turn out
       | that we didn't really need all of the nuclear plants we're
       | currently in the process of setting up to satisfy the power
       | demands of AI data centers?
        
         | NhanH wrote:
         | It seems (feels?) likely that demand for LLM is elastic,
         | especially when it comes to specialized niche. Less power
         | requirements just mean we run more of them in parallel for
         | stuffs, so the power needs is gonna be growing anyway.
        
         | groceryheist wrote:
         | If we're "lucky" (in an AI-optimist sense) we'll need the
         | nuclear plants despite efficiency increases.
        
         | Trasmatta wrote:
         | Are we setting up nuclear plants for AI data centers? If so, I
         | see that as a win all around. We need to rely more on nuclear
         | power, and I'll take whatever we can get to push us in that
         | direction.
        
           | boringg wrote:
           | How else will we get manufacturing gains for a mars base
           | nuclear system?
        
         | fragmede wrote:
         | Jevons paradox says as things get more efficient, usage goes
         | up. In this case, even if AI data centers don't pan out, I
         | think we'll still find use for the electricity they generate.
        
         | tbrownaw wrote:
         | No, as the things using that power get better (newer models
         | keep getting less garbagey) and cheaper (faster hardware and
         | more efficient use of power), people will keep coming up with
         | more things to use them for.
        
         | TkTech wrote:
         | No, not really. AWS getting more power and space efficient
         | chips didn't reduce total power demand, they just added more
         | cores.
         | 
         | Even if the data centers didn't keep up with available
         | capacity, energy demanding industry move to and expand with
         | sources of power, like aluminum production.
        
         | _aavaa_ wrote:
         | Nobody is building nuclear power plants for data centres. A few
         | people have signed some paperwork saying that they would buy
         | electricity from new nuclear plants if they could deliver it at
         | a certain price, a price mind you that has not been done
         | before. Others are trying to restart an existing reactor at
         | three mile island (a thing that has never been done before, and
         | likely won't be done now since the reactor was shut down due to
         | being too expensive to run).
         | 
         | And certainly nobody is building one in the next 3-4 years;
         | they'd be lucky to finish the paperwork in that time.
         | 
         | What is actually going to power them is solar, wind, and
         | batteries:
         | https://www.theverge.com/2024/12/10/24317888/googles-data-ce...
        
           | standeven wrote:
           | And unfortunately, gas and coal in the meantime.
           | 
           | https://www.theguardian.com/technology/2024/sep/15/data-
           | cent...
        
             | robocat wrote:
             | That article is terribly vague.
             | 
             | Electric cars are causing exactly the same problem.
             | 
             | Also the "recs" appear to be based on a lie. Overall, an
             | increase in load can only be green if there is added new
             | green generation to service that load.
        
               | _aavaa_ wrote:
               | Except the alternative to electric are petrol/diesel cars
               | which are worse than electric cars run on gas or coal.
               | The pollution no longer occurs in population zones, and
               | the grid can be cleaned up without changing the car.
               | 
               | The alternatives for these data centres are either build
               | renewables or not build the data centres, both of which
               | are better.
        
           | aitchnyu wrote:
           | Could be a good candidate for factobattery. Overbuild the
           | system, run them at full speed at peak solar generation, then
           | underclock them at night.
           | 
           | https://www.moderndescartes.com/essays/factobattery/
        
             | ForHackernews wrote:
             | This is a really interesting idea! Of course, in practice
             | that will just mean crypto-token mining rather than
             | anything useful.
        
             | numpad0 wrote:
             | Then why no one seem to be doing it?
        
           | adelpozo wrote:
           | Or solar in space, which some have already heard of Lumen
           | Orbit https://www.ycombinator.com/companies/lumen-orbit
        
             | cratermoon wrote:
             | Space-based solar power contains little intrinsic advantage
             | that we can get "only from space." It looks like a wash at
             | best, and the astronomers would say "don't bother."
             | https://dothemath.ucsd.edu/2012/03/space-based-solar-power/
        
               | adelpozo wrote:
               | Yeah, but what I found thought provoking is what if you
               | send the solar panels and the datacenter as well for
               | training. No need to transmission of power down to earth.
               | I guess then it becomes a heat dissipation and hardware
               | upgrade and maintenance. But again, thought provoking.
        
           | cma wrote:
           | > Nobody is building nuclear power plants for data centres. A
           | few people have signed some paperwork saying that they would
           | buy electricity from new nuclear plants if they could deliver
           | it at a certain price, a price mind you that has not been
           | done before.
           | 
           | Not building new, but I think Microsoft paying to restart a
           | reactor at Three Mile Island for their datacenter is much
           | more significant than you make the deals sound:
           | 
           | https://www.theguardian.com/environment/2024/sep/20/three-
           | mi...
        
             | portaouflop wrote:
             | They say it's going to be online in 2028.
             | 
             | Are you willing to bet that they won't have 3 mile island
             | operational by 2030?
        
               | throwup238 wrote:
               | _> Constellation closed the adjacent but unconnected Unit
               | 1 reactor in 2019 for economic reasons, but will bring it
               | back to life after signing a 20-year power purchase
               | agreement to supply Microsoft's energy-hungry data
               | centers, the company announced on Friday._
               | 
               | The reactor they're restarting was operational just five
               | years ago. It's not a fully decommissioned or melted down
               | reactor and it's likely all their licensing is still
               | valid so the red tape, especially environmental studies,
               | is mostly irrelevant. Getting that reactor back up and
               | running will be a lot simpler than building a new one.
        
               | c-linkage wrote:
               | The largest problem will be finding qualified and vetted
               | personnel. All the people who worked at the plant when it
               | closed five years ago had to find jobs elsewhere. Even
               | though the plant was an important employer in Middletown,
               | I don't know if those former employees will be willing
               | the quit there current jobs to go back, especially if
               | there is a risk the plant will just be shut down again
               | when it once again becomes too expensive to operate.
        
             | lopis wrote:
             | It's all been pretty much greenwashing to distract for the
             | real impact of all the AI infrastructure in the energy and
             | water supply.
        
             | _aavaa_ wrote:
             | Microsoft isn't paying to restart. A PPA is a contract
             | saying they will purchase electricity for a specified price
             | for a fixed term. Three Mile Island needs to be able to
             | produce the electricity for the specified price for
             | Microsoft to pay buy it. If it's above that price Microsoft
             | is off the hook.
        
           | yunohn wrote:
           | Look, I agree that nuclear is difficult, but Google and
           | Microsoft have publicly committed to those projects you're
           | mentioning. I don't understand your dismissive tone that all
           | of it is hogwash? This is one of those HN armchair comments.
        
             | dx034 wrote:
             | But not just for AI, for all their data center operations.
        
             | yard2010 wrote:
             | Google and Microsoft won't do anything that doesn't
             | translate to money. These days are over.
        
               | yunohn wrote:
               | Yes, that's why they want to fund and purchase cheap
               | nuclear energy.
        
             | portaouflop wrote:
             | Microsoft also committed publicly to prioritise security.
             | And Google says they prioritise privacy of their users
             | above all else.
             | 
             | I pity the fool that believes anything these corporations
             | put out publicly.
             | 
             | Actions matter, words are wind
        
               | yunohn wrote:
               | I almost feel there's a big difference between the kinds
               | of things we're talking about, but sure.
        
             | oblio wrote:
             | > Google and Microsoft have publicly committed to those
             | projects you're mentioning
             | 
             | Google and Microsoft, or their current CEOs, today?
             | 
             | Amazon's CEO committed to their office employees having
             | flexibility regarding their workplace, only about 2 years
             | ago, yet here we are now, with said employees soon having
             | the flexibility to be 5 days in the office, or quit the
             | company.
             | 
             | CEO promises are not worth the screen time they're
             | provided.
             | 
             | Have these companies signed contracts with major penalties
             | if they back out? Those would basically be the only "close
             | to" unbreakable bonds for them.
        
             | result2vino wrote:
             | I feel like taking Google's commitment to something
             | seriously is one of this things that I can very
             | uncontroversially respond to with "is this your first day?"
             | 
             | All but the biggest Google fanboys know that Google is
             | incredibly indecisive and will cut plans at a moment's
             | notice.
        
               | yunohn wrote:
               | I come to HN for better discussions without such
               | infantile retorts.
        
             | lopis wrote:
             | Because it's all marketing and greenwashing. They are
             | training these models _today_ using fossil fuels. By the
             | time those nuclear reactors are online, they will have
             | gobbled up literally every human creation to train their
             | models multiple times and dried up several water sources.
        
             | _aavaa_ wrote:
             | My tone is because this is a simple predatory delay
             | strategy.
             | 
             |  _Tomorrow, tomorrow, I'll decarbonize tomorrow._
             | 
             | Instead of paying to buy wind and solar plants, which can
             | go up _today_ they are signing a meaningless agreement for
             | _the future_.
             | 
             | A PPA isn't worth the paper it's written on if the seller
             | can't produce electricity at the agreed upon price by the
             | date required.
             | 
             | Take Three Mile Island. It was closed in 2019 since it was
             | uneconomical to run. Since then renewables have continued
             | getting substantially cheaper, while the reactor has been
             | in the process of decommissioning.
             | 
             | Instead of spending money on building wind and solar,
             | Microsoft saw how well Vogtle went and decided that another
             | first of it's kind nuclear project is the best way to make
             | it appear like they're doing something.
        
               | exe34 wrote:
               | I've been told my entire life that it's too late for
               | nuclear, we should have been building them 20 years ago.
               | 
               | I think now's fine, even if it takes time. these
               | companies already buy a ton of power from renewable
               | sources, and it's good to diversify - nuclear is a good
               | backup to have.
        
               | ViewTrick1002 wrote:
               | The west tried building nuclear power 20 years ago. If it
               | had delivered we would be building more now.
               | 
               | It did not deliver. It is time to leave nuclear power to
               | the past just like we have done with the steam engine.
               | 
               | It had its heyday but better cheaper technology replaced
               | it.
        
               | exe34 wrote:
               | what does it mean that "the west tried" - was it a
               | technical failure or was it that people didn't want it in
               | their backyard? just because people hate something
               | doesn't mean that they don't need it. children hate
               | spinach.
        
               | ViewTrick1002 wrote:
               | There was talk of an ongoing nuclear renaissance in the
               | early 2000s. [1]
               | 
               | American companies and utilities announced 30 reactors.
               | Britain announced ~14.
               | 
               | We went ahead and started construction on 7 reactors in
               | Vogtle, Virgil C. Summer, Flamanville, Olkiluoto and
               | Hanhikivi to rekindle the industry. We didn't believe
               | renewables would cut it.
               | 
               | The end result of what we broke ground on is 3 cancelled
               | reactors, 3 reactors which entered commercial operation
               | in the 2020s and 1 still under construction.
               | 
               | The rest are in different states of trouble with
               | financing with only Hinkley Point C slowly moving
               | forward.
               | 
               | In the meantime renewables went from barely existing to
               | dominating new capacity (TWh) in the energy sector.
               | 
               | Today renewables make up 2/3rds of global investment in
               | the energy sector.
               | 
               | The failure of nuclear power is that it is horrifically
               | expensive and the timelines are insane compared to the
               | competition.
               | 
               | Steam locomotives technically work, but are like nuclear
               | power uncompetitive.
               | 
               | Lately nuclear power has caught the imagination of
               | conservative politicians as a method to delay the
               | renewable disruption of the fossil industry and have an
               | answer to climate change.
               | 
               | When their plans, like in Australia, get presented they
               | don't care the slightest about nuclear power and it is
               | only a method to prolong the life of the coal and gas
               | assets.
               | 
               | [1]: https://en.wikipedia.org/wiki/Nuclear_renaissance_in
               | _the_Uni...
        
               | Eisenstein wrote:
               | > American companies and utilities announced 30 reactors.
               | Britain announced ~14.
               | 
               | Lots of projects get announced, they aren't meant to be
               | promises.
               | 
               | > The end result of what we broke ground on is 3
               | cancelled reactors, 3 reactors which entered commercial
               | operation in the 2020s and 1 still under construction.
               | 
               | So there are three operational reactors and another one
               | almost ready. I'm surprised we got that after Fukushima.
               | 
               | > Today renewables make up 2/3rds of global investment in
               | the energy sector.
               | 
               | So we should not invest in anything else?
               | 
               | > Steam locomotives technically work, but are like
               | nuclear power uncompetitive.
               | 
               | This is a terrible analogy.
               | 
               | > Lately nuclear power has caught the imagination of
               | conservative politicians as a method to delay the
               | renewable disruption of the fossil industry and have an
               | answer to climate change.
               | 
               | People who have been advocating for more nuclear power
               | should stop because it is a conservative issue now?
        
               | ViewTrick1002 wrote:
               | Which would have moved forward towards completion if the
               | economic calculus made sense.
               | 
               | We should of course continue with basic research. But,
               | without some incredible breakthrough nuclear power will
               | only serve climate change deniers agenda in delaying the
               | renewable buildout.
               | 
               | This is what you sign up for when proposing investing in
               | nuclear power in 2024:
               | 
               | > The opposition last week released modelling of its
               | "coal-to-nuclear" plan that would slow the rollout of
               | renewable energy and batteries and instead rely on more
               | fossil fuel generation until a nuclear industry could be
               | developed, mostly after 2040.
               | 
               | https://www.theguardian.com/australia-
               | news/2024/dec/16/coali...
        
               | exe34 wrote:
               | in other words, it's too late to build nuclear, let's
               | bury our heads in the sand and hope somehow we have
               | enough renewable in 20 years and we're not still using
               | the coal/gas.
        
               | ViewTrick1002 wrote:
               | The bury our heads in the sand part seems to be you
               | projecting.
               | 
               | The research disagrees with you. Whenever new built
               | nuclear power is included in the analysis the results
               | becomes prohibitively expensive.
               | 
               | > Focusing on the case of Denmark, this article
               | investigates a future fully sector-coupled energy system
               | in a carbon-neutral society and compares the operation
               | and costs of renewables and nuclear-based energy systems.
               | 
               | > The study finds that investments in flexibility in the
               | electricity supply are needed in both systems due to the
               | constant production pattern of nuclear and the
               | variability of renewable energy sources.
               | 
               | > However, the scenario with high nuclear implementation
               | is 1.2 billion EUR more expensive annually compared to a
               | scenario only based on renewables, *with all systems
               | completely balancing supply and demand across all energy
               | sectors in every hour*.
               | 
               | > For nuclear power to be cost competitive with
               | renewables an investment cost of 1.55 MEUR/MW must be
               | achieved, which is substantially below any cost
               | projection for nuclear power.
               | 
               | https://www.sciencedirect.com/science/article/pii/S030626
               | 192...
               | 
               | Or if you want a more southern latitude you have
               | Australia here:
               | 
               | https://www.csiro.au/-/media/Energy/GenCost/GenCost2024-2
               | 5Co...
        
               | Eisenstein wrote:
               | It may cost more, but it is constant generation, and we
               | should invest in as many carbon neutral alternatives as
               | possible that are feasible. The fact that you have a
               | political opposition to it because of conservative
               | opportunists using it for their own agenda is irrelevant.
        
               | ViewTrick1002 wrote:
               | Which is not what any modern grid needs? We need cheap
               | dispatchable power, not horrifically expensive inflexible
               | power.
               | 
               | Many grids around the world already spend loads of time
               | with renewables filling 100% of the demand.
               | 
               | https://www.power-technology.com/news/california-
               | achieves-10...
               | 
               | That is a down right hostile environment for nuclear
               | power which relies on being able to output at 100% 24/7
               | all year around to only be horrifically expensive.
               | 
               | In the land of infinite resources and infinite time "all
               | of the above" is a viable answer. In the real world we
               | neither have infinite resources nor infinite time to fix
               | climate change.
               | 
               | Lets focus our limited resources on what works and
               | instead spend the big bucks on decarbonizing truly hard
               | areas like aviation, construction, shipping and
               | agriculture.
        
               | Eisenstein wrote:
               | 'Plenty of places' is not all places and you want to
               | completely count out a significant energy generating
               | ability because you are annoyed that it doesn't agree
               | with your politics. If it isn't feasible then they won't
               | build it -- by going around and advocating against it you
               | are doing the same thing that happened in the 70s and 80s
               | -- removing a perfectly valid option for energy that we
               | _need_ and will otherwise be fulfilled in any other way
               | if not provided -- almost always with fossil fuels. If
               | you can guarantee every place for all time will be fine
               | with renewables, I 'd like to see it, otherwise, why not
               | step back and let engineers and scientists evaluate
               | instead of grandstanding against an option?
        
               | ViewTrick1002 wrote:
               | What places aren't covered by the spectrum with Denmark
               | for higher latitudes and Australia for the near the
               | equator?
               | 
               | I'm advocating against wasting public money on nuclear
               | power pretending it is a solution to climate change.
               | 
               | Have at it with your own money.
               | 
               | I already provided you with the scientists and engineers,
               | but you seem to have completely disregarded them because
               | they did not align with what you wanted.
               | 
               | I can do it again:
               | 
               | The research disagrees with you. Whenever new built
               | nuclear power is included in the analysis the results
               | becomes prohibitively expensive.
               | 
               | > Focusing on the case of Denmark, this article
               | investigates a future fully sector-coupled energy system
               | in a carbon-neutral society and compares the operation
               | and costs of renewables and nuclear-based energy systems.
               | 
               | > The study finds that investments in flexibility in the
               | electricity supply are needed in both systems due to the
               | constant production pattern of nuclear and the
               | variability of renewable energy sources.
               | 
               | > However, the scenario with high nuclear implementation
               | is 1.2 billion EUR more expensive annually compared to a
               | scenario only based on renewables, *with all systems
               | completely balancing supply and demand across all energy
               | sectors in every hour*.
               | 
               | > For nuclear power to be cost competitive with
               | renewables an investment cost of 1.55 MEUR/MW must be
               | achieved, which is substantially below any cost
               | projection for nuclear power.
               | 
               | https://www.sciencedirect.com/science/article/pii/S030626
               | 192...
               | 
               | Or if you want a more southern latitude you have
               | Australia here:
               | 
               | https://www.csiro.au/-/media/Energy/GenCost/GenCost2024-2
               | 5Co...
        
               | signatoremo wrote:
               | The logic is pretty straightforward I'm not sure what
               | your complaint is. They don't need the power now, but
               | they calculate that they'd need much more power in the
               | future than non nuclear ways of power generation would be
               | able to give them in the same timeframe.
               | 
               | The US is already adding record amount of solar and wind
               | power to replace coal and natural gas plants. What makes
               | you believe Microsoft can just buy more renewable
               | energies? Did you privy to the terms and conditions of
               | the PPA?
               | 
               | The alternative to Three Miles Island restart would be to
               | add natural gas plants, or to buy renewable energy at
               | higher price. I'm sure they have plan B.
        
               | yunohn wrote:
               | > Instead of paying to buy wind and solar plants
               | 
               | Have you considered googling and checking your
               | assumptions? May help clear up the cynical
               | misunderstandings you appear to have.
               | 
               | If you had, you would've read that both Microsoft and
               | Google invest heavily into wind and solar, and that
               | Google is the largest corporate purchaser of renewables
               | in the world. I'm not advocating for these companies,
               | just trying to show that tech is one of the few
               | industries that does actually care and invest into clean
               | energy.
               | 
               | Some sources:
               | 
               | - https://www.gstatic.com/gumdrop/sustainability/google-2
               | 024-e...
               | 
               | - https://www.latitudemedia.com/news/googles-largest-
               | wind-inve...
               | 
               | - https://amp.theguardian.com/technology/2019/sep/20/goog
               | le-sa...
               | 
               | - https://www.theverge.com/2024/5/2/24147153/microsoft-
               | ai-data...
        
               | _aavaa_ wrote:
               | > Have you considered googling and checking your
               | assumptions? May help clear up the cynical
               | misunderstandings you appear to have.
               | 
               | I don't have any such misunderstanding. Perhaps consider
               | seeing my original comment which links to an article
               | describing Google building out solar and wind farms for
               | its data centres.
               | 
               | My cynicism, which I argue is well founded, is based
               | around tech companies signing such agreements with
               | nuclear companies, especially when it involves doings
               | things that have never been done before (restarting
               | reactors and building economical SMRs, see Nuscale...).
               | 
               | All these agreements are likely to amount to nothing more
               | than positive PR, greenwashing, or predatory delay. Yes,
               | they also build out solar and wind, but their nuclear
               | PPAs are given equal standing with projects which
               | actually are likely to be built; so instead of having to
               | build more solar and wind today for more real money, they
               | can promise to buy nuclear tomorrow for no cost today.
        
           | ranyume wrote:
           | > Nobody is building nuclear power plants for data centres
           | 
           | Argentina just announced they're building nuclear plants for
           | AI.
        
         | sbierwagen wrote:
         | Congrats, you have independently reinvented the Hardware
         | Overhang hypothesis: that early AGI could be very inefficient,
         | undergo several optimization passes, and go from needing a
         | datacenter of compute to, say, a single video game console's
         | worth:
         | https://www.lesswrong.com/posts/75dnjiD8kv2khe9eQ/measuring-...
         | 
         | In that scenario, you can go from 0 independent artificial
         | intelligences to tens of millions of them, very quickly.
        
           | UltraSane wrote:
           | it would seem perfectly reasonable to expect the first AIs to
           | be very unoptimized and if the AIs are any good they will be
           | able to optimize themselves a lot and even help design ASICs
           | to help run them.
        
           | philipswood wrote:
           | Thanks for sharing. Worth its own submission:
           | https://news.ycombinator.com/newest
        
         | ilaksh wrote:
         | I think they can easily eat up the new capacity with larger
         | multimodal models that ground language on video.
        
         | mvkel wrote:
         | You have it flipped. But it's both.
         | 
         | AI compute is measured in gigawatts, not gigaflops.
         | 
         | It's "how any gigawatts of compute can we get allocated?"
         | 
         | Not
         | 
         | "How much compute can we fit inside of a gigawatt?"
         | 
         | There's no such thing as "enough"
        
         | owenpalmer wrote:
         | No. This is a classic case of Jevon's paradox. Increased
         | efficiency in resource use can lead to increased consumption of
         | that resource, rather than decreased consumption.
         | 
         | Example:
         | 
         | 1. To decrease total gas consumption, more fuel efficient
         | vehicles are invented.
         | 
         | 2. Instead of using less gas, people drive _more miles_. They
         | take longer road trips, commute farther for work, and more
         | people can now afford to drive.
         | 
         | 3. This increased driving leads to higher overall gasoline
         | consumption, despite each car using gas more efficiently.
        
           | baq wrote:
           | See also https://en.m.wikipedia.org/wiki/Induced_demand
        
             | bonoboTP wrote:
             | How do you argue that demand was induced as opposed to
             | existing demand served?
        
               | oblio wrote:
               | Ok, not maybe instead of calling it "induced", call it
               | "latent demand" if you prefer.
               | 
               | People will do whatever's more convenient, so if you make
               | driving far more convenient than everything else
               | ("cheaper"/"more available"), they will drive.
               | 
               | However convenience should not be the only factor for
               | social decisions. To take this to extremes, it would be
               | much more convenient for J. Doe to steal a car than to
               | buy it, so we definitely do not want to make theft
               | convenient.
        
               | michaelhoney wrote:
               | Yes, the term is a bit clumsy. The way I think of it,
               | people have desires (to drive on the highway), but are
               | dissuaded from doing so by disincentives (it's too busy).
               | Adding a lane reduces the disincentive, so that latent
               | desire is satisfied, until it reaches a new equilibrium.
        
               | HPsquared wrote:
               | Result: more people getting where they want to go.
        
               | treyd wrote:
               | But in the case of highways, they probably would have
               | still gotten where they want to go by another route. The
               | folly is treating highway capacity as being a "market"
               | when really the decision making is much more dynamic and
               | nuanced.
        
               | HPsquared wrote:
               | Like a market it's very complicated with many feedbacks
               | and value judgements. For example "How much of my time is
               | it worth sitting in traffic to get to my preferred store
               | across town vs the closer one?"
               | 
               | It's a bit like queueing. The cost isn't monetary.
        
               | bonoboTP wrote:
               | But sometimes the social environment adapts and now you
               | have to drive that amount because it got factored in and
               | things are now built further away, so whether you want to
               | go far is not up to you. See long commutes becoming the
               | norm. Now, arguably long commutes lead to better job
               | allocations and more efficient land use as people can
               | live in one place and work in any of the workplaces
               | within a large radius. So it's a bit more complicated
               | than "want", but ultimately more value seems to be
               | produced.
        
               | kaibee wrote:
               | > ultimately more value seems to be produced.
               | 
               | Is more value produced or are costs just shifted off the
               | balance sheet onto the public commons? Driving instead of
               | walking/public transit has certainly been profitable for
               | some people/companies. But it has also been less than
               | ideal from a public health standpoint. And the time spent
               | commuting is unpaid, so while the business saves money on
               | rent, the increase in travel time is still a cost borne
               | by society as a whole. I would describe this as the
               | opposite of 'efficient land use' personally.
        
               | fauigerzigerk wrote:
               | Because economists only call it demand to the extent that
               | people are willing and able to make a purchase.
               | 
               | If someone has a need or wants something real bad but
               | can't afford to buy the desired quantity at the
               | prevailing price then economists don't call it demand.
        
               | Joker_vD wrote:
               | Maybe because of an extremely aggressive marketing, and
               | pushing "AI features" into literally everything, and
               | there being a pushback against that?
        
           | bonoboTP wrote:
           | There's no paradox in that. People became more capable and
           | can afford to do more.
        
             | mewpmewp2 wrote:
             | Also I think this will play out for AI as a productivity
             | multiplier. Instead of people having less work there will
             | be more to do since more things are worth doing now. For
             | the following few years at least.
        
               | HPsquared wrote:
               | Work expands to fill the available time, after all.
        
             | oreilles wrote:
             | It is a paradox because there is an apparent contradiction
             | in the fact that higher efficiency leads to higher
             | consumption. By definition the opposite should be true.
        
               | bonoboTP wrote:
               | I don't share that intuition. If I earn more money, I
               | won't necessarily save more. I'll buy better food, better
               | clothes, better everything and live a materially more
               | prosperous life. My savings rate may even go down. Or up.
               | It depends on the specifics. When a tech gets more
               | efficient, it causes people to do more. To shape their
               | surroundings and bend reality more to their will. If you
               | can travel easier, you can realize your travel wishes
               | better.
        
             | crazygringo wrote:
             | Really, once you understand any "paradox", it ceases to be
             | a paradox at all.
             | 
             | I always feel a bit silly referring to any "paradox" as
             | such, when it's _not_ a paradox anymore. When it now makes
             | perfect sense.
        
           | banannaise wrote:
           | [nitpick] it's the Jevons Paradox, named for William Stanley
           | Jevons. No apostrophe, but if you were to add one, it would
           | be Jevons' Paradox.
           | 
           | https://en.wikipedia.org/wiki/William_Stanley_Jevons
        
         | m463 wrote:
         | Don't you think people will just add better models to meet
         | available memory?
         | 
         | If we run 7B now, why wouldn't we run 700b with memory
         | optimizations?
        
         | lm28469 wrote:
         | It's called the rebound effect, at no point in modern history
         | efficiency reduced our energy needs, we just use the extra
         | energy to either run more of the same thing or run other things
        
         | ndr wrote:
         | Wirth's law: software is getting slower more rapidly than
         | hardware is becoming faster.
         | 
         | I think there's the energy parallel: Software is becoming more
         | energy-hungry faster than algorithms are becoming efficient.
         | 
         | So we'll still need the energy.
        
         | thom wrote:
         | What if it's a big hoax and we create a better world for
         | nothing?
        
         | huijzer wrote:
         | I guess power demands will slowly grow. The same happened with
         | compute in general. Compared to 1960, we have several orders of
         | magnitude more compute but also several orders of magnitude
         | more efficient compute. Data centers are currently about 0.4%
         | of total energy use (electricity is about 20% of total energy
         | use and of the electricity about 2% goes to data centers, so
         | 20% * 2% = 0.4%).
        
         | amelius wrote:
         | No idea, but it may also turn out that OpenAI has no moat,
         | which is more interesting.
        
         | hoseja wrote:
         | Then you can simply have more AI in the data centres.
        
         | hagbard_c wrote:
         | That'd give a lot of extra power which can be used for other -
         | and probably better - purposes so I'd say let them build those
         | plants. The more power available the better after all?
        
         | narrator wrote:
         | Jevons Paradox will take care of it[1]. The more efficiently a
         | resource is used, the more demand there is for it.
         | 
         | The grave implication of Jevons paradox is that the fundamental
         | conflict between sustainability and economic progress is not
         | resolved solely by using resources more efficiently. It's a
         | theory of supply chain constraints essentially. Once a resource
         | is used more efficiently, its use is increased until the next
         | most economically constrained resource hits its economically
         | useful limit.
         | 
         | [1] https://en.wikipedia.org/wiki/Jevons_paradox
        
         | the8472 wrote:
         | We don't even know a tighter lower bound for matrix multiplies
         | than O(n2). Naive is O(n3), strassen is O(n^2.8). And those are
         | simple, low-level kernels. At the higher level we also do not
         | know tight lower bounds. But we do know some loose bounds from
         | nature, e.g. how much data and energy a human consumes over its
         | lifetime.
        
       | ironfootnz wrote:
       | I'm a big fan of their papers, this one didn't disappoint
        
       | gcanyon wrote:
       | Given that the algorithms powering present LLM models hadn't been
       | invented ten years ago, I have to think that they are
       | (potentially) _far_ from optimal.
       | 
       | Brains have gone through millions of iterations where being
       | efficient was a huge driver of success. We should not be
       | surprised if someone finds a new ML method that is both wildly
       | more efficient and wildly more effective.
        
         | mycall wrote:
         | Perhaps LLM++ will start iterating the algorithms via synthetic
         | data until they are far more optimal
        
       | solarkraft wrote:
       | It's mind bogglingly crazy that language models rivaling ones
       | that used to require huge GPUs with a ton of VRAM to run now run
       | on my upper-mid-range laptop from 4 years ago. At usable speed.
       | Crazy.
       | 
       | I didn't expect capable language models to be practical/possible
       | to run loyally, much less on hardware I already have.
        
         | baq wrote:
         | You have a sota multi-modal LLM running in your head at 20W,
         | shared with best in class sensor package and top performing
         | robotics control unit.
         | 
         | There's soooo much more to optimize.
        
           | fecal_henge wrote:
           | But can it know love?
        
             | baq wrote:
             | Word on the street is researchers looked at the weights and
             | weights looked back. You'll have to ask the weights.
        
           | myrmidon wrote:
           | I would argue that our sensor package is losing its lead very
           | quickly-- audio performance is already on par with current
           | tech and image processing is closing the gap very quickly as
           | well (it helps a lot that silicon-based technology is much
           | less constrained on bandwidth). Tactile sensing is still
           | lightyears ahead, and I don't see that situation improving
           | anytime soon...
        
             | IWeldMelons wrote:
             | chemical sensing is still quite good though.
        
         | prox wrote:
         | I might have a go at installing one, what is a good source or
         | install at the moment?
        
           | wint3rmute wrote:
           | Ollama was the easiest way to set up local LLMs for me.
           | 
           | https://ollama.com/
        
             | solarkraft wrote:
             | With llama3.2:1b, llama3.2:3b and llama 3.1:8b being the
             | main ones I tried and found impressive.
        
           | spacemanspiff01 wrote:
           | lmstudio is very easy if you are running on local desktop.
        
           | Alifatisk wrote:
           | msty.app is good
        
           | Eisenstein wrote:
           | If you don't care about docker packages being used as
           | installers and your home directory invisibly used to store
           | massive weight files in exchange for not having to deal with
           | learning any configuration: ollama or lmstudio.
           | 
           | If you just want to play for a bit: llamafile
           | 
           | If you want granular control with ease of execution in
           | exchange for having to figure out what the settings mean and
           | figure out which weights to download: koboldcpp. (check out
           | bartowski on huggingface for the weights)
           | 
           | These are all based on llamacpp as a backend, by the way.
        
         | mandmandam wrote:
         | > I didn't expect capable language models to be
         | practical/possible to run _loyally_
         | 
         | Now there's a fun typo. Hopefully not too much fun.
        
           | momojo wrote:
           | That sentence triggered memories of reading the huge
           | paperback Asimov compilation my mom kept on the bookshelf as
           | a kid.
        
       | bamboozled wrote:
       | Really exciting news.
        
       | Euphorbium wrote:
       | Stop words in extra steps.
        
       | aussieguy1234 wrote:
       | Most people don't remember absolutely everything, just the
       | important stuff.
        
       | hoc wrote:
       | And we finally can sell the unoptimized models as Hires (since I
       | can still read the differences!).
        
       | cs702 wrote:
       | Very clever, very meta, and it seems to work really well.
       | 
       | The two big take-aways for me are:
       | 
       | * It's possible to train a model to learn to summarize context
       | from the _attention matrix_ , based only on dot-product scores (k
       | @ q.T * mask), _regardless of how tokens are embedded_.
       | 
       | * Once the model is trained, it will work with _any_ attention
       | matrix, even if it 's the attention matrix of another model.
       | 
       | I've added this to my ever-growing list of things to try.
        
         | xpl wrote:
         | Is there any intuition why does it even work? It seems very
         | unexpected.
        
       | skellington wrote:
       | This only reduces the working memory, not the base model itself?
        
       ___________________________________________________________________
       (page generated 2024-12-17 23:01 UTC)