[HN Gopher] Snorting the AGI with Claude Code
       ___________________________________________________________________
        
       Snorting the AGI with Claude Code
        
       Author : beigebrucewayne
       Score  : 109 points
       Date   : 2025-06-16 11:01 UTC (11 hours ago)
        
 (HTM) web link (kadekillary.work)
 (TXT) w3m dump (kadekillary.work)
        
       | dwohnitmok wrote:
       | On the one hand very cool.
       | 
       | On the other hand, every time people are just spinning off sub-
       | agents I am reminded of this:
       | https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality...
       | 
       | It's simultaneously the obvious next step and portends a
       | potentially very dangerous future.
        
         | TeMPOraL wrote:
         | > _It 's simultaneously the obvious next step_
         | 
         | As it has been _over three years ago_ , when that was
         | originally published.
         | 
         | I'm continuously surprised both by how fast the models
         | themselves evolve, and _how slow their use patterns are_. We
         | 're still barely playing with the patterns that were obvious
         | _and_ thoroughly discussed back before GPT-4 was a thing.
         | 
         | Right now, the whole industry is obsessed with "agents", aka.
         | giving LLMs function calls and _limited_ control over the loop
         | they 're running under. How many years before the industry will
         | get to the point of giving LLMs proper control over the top-
         | level loop _and_ managing the context, plus an ability to
         | "shell out" to "subagents" as a matter of course?
        
           | qsort wrote:
           | > How many years before the industry will get to the point
           | 
           | When/if the underlying model gets good enough to support that
           | pattern. As an extreme example, you aren't ever going to make
           | even a basic agent with GPT-3 as the base model, the juice
           | isn't worth the squeeze.
           | 
           | Models have gotten way better and I'm now convinced (new data
           | -> new opinion) that they are a major win for coding, but
           | they still need a lot, _a lot_ of handholding, left to their
           | own devices they just make a mess.
           | 
           | The underlying capabilities of the model are the entire
           | ballgame, the "use patterns" aren't exactly rocket science.
        
           | benlivengood wrote:
           | We haven't hit the RSI threshold yet and so evolution is so
           | slow that it's usually terminated as not-useful or it solves
           | a concrete problem and is terminated by itself or a human.
           | Earlier model+frameworks merely petered out almost
           | immediately. I'm guessing it's roughly correlated with the
           | progress on METR.
        
       | SamPatt wrote:
       | >Claude code feels more powerful than cursor, but why? One of the
       | reasons seems it's ability to be scripted. At the end of the day,
       | cursor is an editor, while claude code is a swiss army knife (on
       | steroids).
       | 
       | Agreed, and I find that I use Claude Code on more than
       | traditional code bases. I run it in my Obsidian vault for all
       | kinds of things. I run it to build local custom keyboard bindings
       | with scripts that publish screenshots to my CDN and give me a
       | markdown link, or to build a program that talks to Ollama to
       | summarize my terminal commands for the last day.
       | 
       | I remember the old days of needing to figure out if the
       | formatting changes I wanted to make to a file were sufficient to
       | build a script or just do them manually - now I just run Claude
       | in the directory and have it done for me. It's useful for so many
       | things.
        
         | jjice wrote:
         | I'm very interested to hear what your uses cases are when using
         | it in your Obsidian Vault
        
         | Aeolun wrote:
         | The thing is, Claude Code only works if you have the plan. It's
         | impossible to use it on the API, and it makes me wonder if
         | $100/month is truly enough. I use it all day every day now, and
         | I must be consuming a whole lot more than my $100 is worth.
        
           | sorcerer-mar wrote:
           | > It's impossible to use it on the API
           | 
           | What does this mean?
        
           | ggsp wrote:
           | You can definitely use Claude Code via the API
        
           | practal wrote:
           | I think it is available on Claude Pro now, so just $20.
        
       | tinyhouse wrote:
       | This article is a bit all over the place. First, a slide deck to
       | describe a codebase is not that useful. There's a reason why no
       | one ever uses a slide deck for anything besides supporting an
       | oral presentation.
       | 
       | Most of these things in the post aren't new capabilities. The
       | automation of workflows is indeed valuable and cool. Not sure
       | what AGI has anything to do with it.
        
         | bravesoul2 wrote:
         | Also I don't trust it. They touched on that I think (I only
         | skimmed).
         | 
         | Plus you shouldn't need an LLM to understand a codebase. Just
         | make it more understandable! Of course capital likes shortcuts
         | and hacks to get the next feature out in Q3.
        
           | imiric wrote:
           | > Plus you shouldn't need an LLM to understand a codebase.
           | Just make it more understandable!
           | 
           | The kind of person who prefers this setup wants to read (and
           | write) the least amount of code on their own. So their ideal
           | workflow is one where they get to make programs through
           | natural language. Making codebases understandable for this
           | group is mostly a waste of effort.
           | 
           | It's a wild twist of fate that programming languages were
           | intended to make programming friendly to humans, and now
           | humans don't want to read them at all. Code is becoming just
           | an intermediary artifact useless to machines, which can
           | instead write machine code directly.
           | 
           | I wish someone could put this genie back in the bottle.
        
           | lelandbatey wrote:
           | There is no amount of static material that will perfectly
           | conform to the shape and contours of every mind that consumes
           | that static material such that they can learn what they want
           | to learn when they want to learn it.
           | 
           | Having a thing that is interactive and which can answer
           | questions is a very useful thing. A slide deck that sits
           | around for the next person is probably not that great, I
           | agree. But if you desperately want a slide deck, then an
           | agent like Claude which can create it on demand is pretty
           | good. If you want summaries of changes over time, or to know
           | "what's the _overall_ approach at a jargon-filled but still
           | overview level explanation of how feature /behavior X is
           | implemented?", an agent can generate a mediocre (but probably
           | serviceable) answer to any of those by reading the repo.
           | That's an amazing swiss-army knife to have in your pocket.
           | 
           | I really used to be a hater, and I really did not trust it,
           | but just using the thing has left me unable to deny its
           | utility.
        
         | Uehreka wrote:
         | > Not sure what AGI has anything to do with it.
         | 
         | Judging from the tone of the article, they're using the term
         | AGI in a jokey way and not taking themselves too seriously,
         | which is refreshing.
         | 
         | I mean like, it wouldn't be refreshing if the article didn't
         | also have useful information, but I do actually think a slide
         | deck could be a useful way to understand a codebase. It's
         | exactly the kind of nice-to-have that I'd never want a junior
         | wasting time on, but if it costs like $5 and gets me something
         | minorly useful, that's pretty cool.
         | 
         | Part of the mind-expanding transition to using LLMs involves
         | recognizing that there are some things we used to dislike
         | because of how much effort they took relative to their worth.
         | But if you don't need to do the thing yourself or burn through
         | a team member's time/sanity doing it, it can make you start to
         | go "yeah fuck it, trawl the codebase and try to write a
         | markdown document describing all of the features and
         | requirements in a tabular format. Maybe it'll go better than I
         | expect, and if it doesn't then on to something else."
        
       | abhisheksp1993 wrote:
       | ``` claude --dangerously-skip-permissions # science mode ```
       | 
       | This made me chuckle
        
       | 42lux wrote:
       | If people would be as patient and inventive to teach junior devs
       | as they are with llms the whole industry would be better of.
        
         | sorcerer-mar wrote:
         | You pay junior devs way way way more money for the privilege of
         | them being bad.
         | 
         | And since they're human, the juniors themselves do not have the
         | patience of an LLM.
         | 
         | I _really_ would not want to be a junior dev right now... Very
         | unfair and undesirable situation they 've landed in.
        
           | mentos wrote:
           | At least it's easier to teach yourself anything now with an
           | LLM? So maybe it balances out.
        
             | sorcerer-mar wrote:
             | I think it's actually even worse: it's easier to _trick
             | yourself_ into thinking you 're teaching yourself anything.
             | 
             | Learning comes from grinding and LLMs are the ultimate
             | anti-intellectual-grind machines. Which is great for when
             | you're not trying to learn a skill!
        
               | jyounker wrote:
               | Yeah, you have to be really careful about how you use
               | LLMs. I've been finding it very useful to use them as
               | teachers, or to use them in the same way that I'd use a
               | coworker. "What's the idiomatic ways to write this python
               | comprehension in javascript?" Or, "Hey, do you remember
               | what you call it when..." And when I request these things
               | I'll try to ask in the most generic way possible so that
               | I then get retype the relevant code, filling in the
               | blanks with my own values.
               | 
               | That's just one use though. The other is treating it like
               | it's a jr developer, which has its own shift in thinking.
               | Practice in writing details specs goes a long way here.
        
               | sorcerer-mar wrote:
               | 100% agreed.
               | 
               | > Practice in writing details specs goes a long way here.
               | 
               | This is an additional asymmetric advantage to more senior
               | engineers as they use these tools
        
           | drewlesueur wrote:
           | I think it would be great to be a junior dev now and be able
           | to learn quickly with llms.
        
         | godelski wrote:
         | A constant reminder: you can't have wizards without having
         | noobs.
         | 
         | Every wizard was once a noob. No one is born that way, they
         | were forged. It's in everybody's interest to train them. If
         | they leave, you still benefit from the other companies who
         | trained them, making the cost equal. Though if they leave,
         | there's probably better ways to make them stay that you haven't
         | considered (e.g. have you considered not paying new juniors
         | more than your current junior that has been with the company
         | for a few years? They should be able to get a pay bump without
         | leaving)
        
           | QuantumGood wrote:
           | I think too many see it more as "every stem cell has the
           | potential to be any [something]", but it's generally better
           | to let them self differentiate until survivors with more
           | potential exist.
        
           | lunarboy wrote:
           | I'm sure people (esp engineers) know this. But imagine you're
           | starting a company: would you try to deploy N agents (even if
           | shitty), or take a financial/time/legal/social risk with a
           | new hire. When you consider short-term costs, the math just
           | never works out in favor of real humans.
        
             | geraneum wrote:
             | Well, in the beginning, the math doesn't work out in favor
             | of building the software (or the thing you want to sell)
             | either.
        
         | qsort wrote:
         | The vilification of juniors and the abandonment of the idea
         | that teaching and mentoring are worthwhile are single-handedly
         | making me speedrun burnout. May a hundred years of Microsoft
         | Visio befall anybody who thinks that way.
        
         | handfuloflight wrote:
         | Took a junior dev under my wings recently and the more time and
         | energy and resources I spent on on him, the more expectation
         | and disrespect I was shown.
         | 
         | "Familiarity breeds contempt."
         | 
         | None of my instances with AI have shown me contempt.
        
       | jasonthorsness wrote:
       | The terminal really is sort of the perfect interface for an LLM;
       | I wonder whether this approach will become favored over the
       | custom IDE integrations.
        
         | drcode wrote:
         | sort of, except I think the future of llms will be to to have
         | the llm try 5 separate attempts to create a fix in parallel,
         | since llm time is cheaper than human time... and once you
         | introduce this aspect into the workflow, you'll want to spin up
         | multiple containers, and the benefits of the terminal aren't as
         | strong anymore.
        
           | jyounker wrote:
           | Having command line tools to spin up multiple containers and
           | then to collect their results seems like it would be a pretty
           | natural fit.
        
       | intralogic wrote:
       | How can I make this page easier to read in chrome? The gray-on-
       | gray doesn't have enough contrast for me to read easily.
        
       | bionhoward wrote:
       | Assuming attention to detail is one of the best signs people give
       | a fuck about craftsmanship, isn't the fact the Anthropic legal
       | terms are logically impossible to satisfy a bad sign for their
       | ability to be trusted as careful stewards of ASI?
       | 
       | Not exactly "three laws safe" if we can't use the thing for work
       | without violating their competitive use prohibition
        
       ___________________________________________________________________
       (page generated 2025-06-16 23:00 UTC)