[HN Gopher] How to enhance generative AI's problem-solving capab...
___________________________________________________________________
How to enhance generative AI's problem-solving capabilities, boost
productivity
Author : monkeydust
Score : 32 points
Date : 2024-05-26 17:15 UTC (5 hours ago)
(HTM) web link (blogs.lse.ac.uk)
(TXT) w3m dump (blogs.lse.ac.uk)
| smarm52 wrote:
| A nice summary of an idea similar to Multi-Agent Systems.
|
| https://en.wikipedia.org/wiki/Multi-agent_system
| NicoJuicy wrote:
| These things will have the same flaw as no-code tools.
|
| No one is going to remember how the system works and all those
| prompt engineers are going to find out that programming languages
| are well documented, but things like migrations, multitenancy,
| ... aren't.
|
| Good luck when an AI api implements a breaking change in an API
| and people rely on it.
|
| Or when a issue happens and it can't find logs, ... ( If it was
| even implemented :p )
| Animats wrote:
| The article starts out as if it's headed for "and that's how we
| did it". But no. There's no implementation.
|
| _" Imagine a virtual team of AI agents, each with its workflow's
| own specialism, collaborating to solve problems and make
| decisions just like a human team would."_
|
| OK. Where does that go? So far, multi-agent systems have been
| delegating simple and well-bounded tasks, such as "fetch the
| weather info for Outer Nowhere" or "check airline schedules for
| flights from JFK to ORD", or even "what is 25% of $50". Those are
| questions inexpensive to answer, and don't need much management.
| If the subagents are complex, they will need management, and
| probably budgeting. Subagents need to know when to stop and when
| to approximate. If the subagents are themselves generative AI
| systems, there's potential for hallucination at the lower levels
| generating info that the higher levels take as valid. Subagents
| also need to be able to query their managers - "is this enough
| detail" is a reasonable question to pass upwards. They may need
| to talk to their peer agents.
|
| Now you have all the problems of organizational dynamics within a
| multi-agent AI system.
|
| I look forward to reading papers with titles such as:
|
| - "Teams of generative AI agents for coding - scrum or
| waterfall?"
|
| - "Span of control - how many subagents should an agent manage?"
|
| - "Does the agent org chart influence the solution too much?"
|
| - "Resolving disagreements between specialized subagents".
|
| That's where this is going. It has to. Once you start to cut a
| problem into pieces to be handled by different units, all those
| problems arise.
| fsndz wrote:
| this is why I have been arguing there will be no AGI
| https://www.lycee.ai/blog/why-no-agi-openai
| prox wrote:
| Its a goal looking for a problem, aka AI hype. It's the big
| thing now, like NFTs before.
|
| I agree with your blog, the definition itself is vague, and
| what people want to get out of it as well. There is a big
| "we'll figure it out when we get there" attitude it seems to
| me.
|
| Imagine a society where everything can be and is done by AGI
| (and its drones) what then? What do we want out of it? What
| will define humans in such an environment?
| pessimizer wrote:
| It's wonderful to have new problems to solve. I'm looking
| forward to Robert's Rules of Order finally being considered a
| networking protocol between autonomous agents.
| exe34 wrote:
| those agents might end up with the same solution we came up
| with - endless meetings and then make the simplest piece of
| crap possible to meet half of the requirements.
| interstice wrote:
| Maybe this is why multi agents are not the answer, or at least
| not in an individualist proto human sense.
|
| But does every agent have to be completely separate or could
| this kind of process land somewhere in sub-surface level
| processing within a single model?
|
| We are already there in some ways with node clusters handling
| specific subjects at the lowest levels - even being standard
| human is like being a large collection of processes all running
| in parallel.
| Animats wrote:
| > But does every agent have to be completely separate or
| could this kind of process land somewhere in sub-surface
| level processing within a single model?
|
| Some agents won't be LLMs.
|
| Wolfram Alpha (now with ChatGPT) is close to this type of
| system.
| schmidtleonard wrote:
| > The productivity benefits perhaps take us closer to the
| aspiration Keynes had when he wrote Economic Possibilities for
| our Grandchildren in 1930, in which he forecast that in a hundred
| years, thanks to technological advancements improving the
| standard of living, we could all be doing 15-hour work weeks.
|
| Well, you see, the benefits have to be split between capital and
| labor.
|
| The system is called "capitalism."
|
| Figure it out.
| ben_w wrote:
| We have a higher standard of living than when the book was
| written. Even the basics have changed a lot:
|
| > It wasn't until the 1930s that new houses were built with
| indoor toilets and bathrooms as standard, says Zoe Hendon, head
| of museum collections at Middlesex University's Museum of
| Domestic Design and Architecture. "At that time, bathrooms were
| seen as a luxury."
|
| - https://www.bbc.com/culture/article/20210407-how-the-
| bathroo...
| rakoo wrote:
| Capitalism isn't about standards of livings, it's about
| exploitation of the majority by and for a minority, whther
| you give the exploited schackles or golden shoes.
| prox wrote:
| Yup, if you read the major economic books coming out of the
| last decade, they all have that theme.
| hubraumhugo wrote:
| I recently wrote a blog post about why "AI agents" are still too
| early, too expensive, too unreliable:
| https://www.kadoa.com/blog/ai-agents-hype-vs-reality
|
| The WebArena leaderboard[0], which benchmarks LLM agents against
| real-world tasks, shows that even the best-performing models have
| a success rate of only 35.8%.
|
| [0] https://docs.google.com/spreadsheets/d/1M801lEpBbKSNwP-
| vDBkC...
| chx wrote:
| > How to enhance generative AI's problem-solving capabilities,
|
| A zero multiplied by whatever is still zero.
|
| It can not solve _anything_ with one broad category of exceptions
| as https://hachyderm.io/@inthehands/112006855076082650
| brilliantly explains:
|
| > You might be surprised to learn that I actually think LLMs have
| the potential to be not only fun but genuinely useful. "Show me
| some bullshit that would be typical in this context" can be a
| genuinely helpful question to have answered, in code and in
| natural language -- for brainstorming, for seeing common
| conventions in an unfamiliar context, for having something crappy
| to react to.
|
| > Alas, that does not remotely resemble how people are pitching
| this technology.
___________________________________________________________________
(page generated 2024-05-26 23:01 UTC)