Snorting the AGI with Claude Code

https://kadekillary.work/blog/#2025-06-16-snorting-the-agi-with-claude-code

332 239 1 year ago

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.

TeMPOraL13• 1 year ago

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?

qsort3• 1 year ago

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• 1 year ago

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.

lubujackson• 1 year ago

Am I the only one who saw in the prompt:

${SUGESTION}

And recognized it wouldn't do anything because of a typo? Alas, my kind is not long for this world...

floren• 1 year ago

I noticed it and then scrolled through looking for the place where they called it out... sadly disappointed but I don't know what I expected from lesswrong

SamPatt3• 1 year ago

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• 1 year ago

I'm very interested to hear what your uses cases are when using it in your Obsidian Vault

SamPatt3• 1 year ago

Formatting changes across lots of notes, creating custom plugins, diagnosing problems with community plugins, creating a syncing program that compares my vault (with publish:true frontmatter) to my blog repo and if see changes then automatically updates the repo (which is used to build my site), creating a tool that converts inline urls to markdown footnotes, etc.

Obsidian is my source of truth and Claude is really good at managing text, formatting, markdown, JS, etc. I never let it make changes automatically, I don't trust it that much yet, but it has undoubtedly saved me hours of manual fiddling with plugins and formatting alone.

Aeolun2• 1 year ago

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-mar8• 1 year ago

It’s impossible to use it on the API

What does this mean?

ggsp• 1 year ago

You can definitely use Claude Code via the API

practal• 1 year ago

I think it is available on Claude Pro now, so just $20.

CGamesPlay• 1 year ago

You use it "all day every day", so it makes sense that you would prefer the plan. It's perfectly economical to use it without a plan, if your usage patterns are different. Here's a tool someone else wrote that can help you decide: https://github.com/ryoppippi/ccusage

davidw• 1 year ago

One thing that I am not liking about the LLM world is that it seems to be tilting several things back in favor of BigCorps.

The open source world is one where antirez, working on his own off in Sicily, could create a project like Redis and then watch it snowball as people all over got involved.

Needing a subscription to something only a large company can provide makes me unhappy.

We'll see if "can be run locally" models for more specific tasks like coding will become a thing, I guess.

AstroBen2• 1 year ago

I had an LLM sort a crap-tonne of my notes into category folders the other day. My god that was helpful

cpard• 1 year ago

How do you script Claude code? I've been using it as a CLI but haven't thought of invoking Claude code through a script, sounds very interesting.

dghlsakjg4• 1 year ago

Read the article. Basically just using aliases for specififc prompts.

tinyhouse• 1 year ago

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.

bravesoul22• 1 year ago

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• 1 year ago

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• 1 year ago

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.

groby_b• 1 year ago

Plus you shouldn't need an LLM to understand a codebase. Just make it more understandable!

And fundamentally, that isn't a function of "capital". All code bases are shaped by the implicit assumptions of their writers. If there's a fundamental mismatch or gap between reader and writer assumptions, it won't be readable.

LLMs are a way to make (some of) these implict assumptions more legible. They're not a panacea, but the idea of "just make it more understandable" is not viable. It's on par with "you don't need debuggers, just don't write bugs"

Uehreka• 1 year ago

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.”

sandos• 1 year ago

The number one thing I have found LLMs useful for is producing mermaidjs diagrams of code. Now, I know they are not always perfect but it has been "good enough" very many times, and I have never seen hallucinations here, only omissions. If I notice something missing its super-easy to tell it to amend.

abhisheksp1993• 1 year ago

``` claude --dangerously-skip-permissions # science mode ```

This made me chuckle

BoredPositron2• 1 year ago

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-mar8• 1 year ago

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• 1 year ago

At least it’s easier to teach yourself anything now with an LLM? So maybe it balances out.

drewlesueur• 1 year ago

I think it would be great to be a junior dev now and be able to learn quickly with llms.

fallinditch• 1 year ago

Maybe it's the senior devs who should be the ones to worry?

Seniors' attitudes on HN are often quick to dismiss AI assisted coding as something that can't replace the hard-earned experience and skill they've built up during their careers. Well maybe, maybe not. Senior devs can get a bit myopic in their specializations. Whereas a junior Dev doesn't have so much baggage, maybe the fertile brains of youth are better in times of rapid disruption where extreme flexibility of thought is the killer skill.

Or maybe the whole senior/junior thing is a red herring and pure coding and tech skills are being deflated all across the board. Perhaps what is needed now is an entirely new skill set that we're only just starting to grasp.

yieldcrv• 1 year ago

I really would not want to be a junior dev right now... Very unfair and undesirable situation they've landed in.

I don't really get this, at the beginning of my career I masquaraded as a senior dev with experience as fast as I could until it was laundered into actual experience

Form the LLC and that's your prior professional experience, working for it

I felt I needed to do that and that was way before generative AI, like at least a decade

beefnugs• 1 year ago

See if the promise was real: llms are great skill multipliers! Then it is the new renaissance of one developer businesses popping up left and right every day! Ain't nobody got time for corporate coercion hierarchy nonsense.

Hmm no news about that really

jwr• 1 year ago

You pay junior devs way way way more money for the privilege of them being bad.

Oh, it's worse than that. You do that, and they complain that they are underpaid and should earn much, much more. They also think they are great, it's just you, the old-timer, that "doesn't get it". You invest lots of time to work with them, train them, and teach them how to work with your codebase.

And then they quit because the company next door offered them slightly more money and the job was easier, too.

leptons4• 1 year ago

You pay junior devs way way way more money for the privilege of them being bad.

I hope you don't think that what you're paying for an LLM today is what it actually costs to run the LLM. You're paying a small fraction.

So much investment money is being pumped into AI that it's going to make the 2000 dot-com bubble burst look tiny in comparison, if LLMs don't start actually returning on the massive investments. People are waking up to the realities of what an LLM can and can't do, and it's turning out to not be the genie in the bottle that a lot of hype was suggesting. Same as crypto.

The tech world needs a hype machine and "AI" is the current darling. Movie streaming was once in the spotlight too. "AI" will get old pretty soon if it can't stop "hallucinating". Trust me I would know if a junior dev is hallucinating and if they actually are then I can choose another one that won't and will actually become a great software developer. I have no such hope for LLMs based on my experiences with them so far.

godelski4• 1 year ago

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• 1 year ago

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• 1 year ago

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.

TuringNYC• 1 year ago

> A constant reminder: you can't have wizards without having noobs.

Try telling that to companies with quarterly earnings. Very few resist the urge to optimize for the short term.

qsort3• 1 year ago

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.

empireofdust• 1 year ago

What’s the best implementation of junior training or teaching/mentoring in general within tech that you’ve seen?

jayofdoom• 1 year ago

I spent a lot of time in my career, honestly some of the most impactful stuff I've done, mentoring college students and junior developers. I think you are dead on about the skills being very similar. Being verbose, not making assumptions about existing context, and generalized warnings against pitfalls when doing the sort of thing you're asking it to do goes a long long way.

Just make sure you talk to Claude in addition to the humans and not instead of.

jasonthorsness• 1 year ago

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• 1 year ago

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.

jyounker2• 1 year ago

Having command line tools to spin up multiple containers and then to collect their results seems like it would be a pretty natural fit.

jtms• 1 year ago

Tmux?

peab• 1 year ago

dagger does this: https://www.youtube.com/watch?v=C2g3vdbffOI

sally_glance2• 1 year ago

Who or what will review the 5 PRs (including their updates to automated tests)? If it's just yet another agent, do we need 5 of these reviews for each PR too?

In the end, you either concede control over 'details' and just trust the output or you spend the effort and validate results manually. Not saying either is bad.

cwlb• 1 year ago

https://github.com/dagger/container-use

sothatsit• 1 year ago

I feel like the better approach would be to throw away PRs when they're bad, edit your prompt, and then let the agent try again using the new prompt. Throwing lots of wasted compute at a problem seems like a luxury take on coding agents, as these agents can be really expensive.

So the process becomes: Read PR -> Find fundamental issues -> Update prompt to guide agent better -> Re-run agent.

Then your job becomes proof-reading and editing specification documents for changes, reviewing the result of the agent trying to implement that spec, and then iterating on it until it is good enough. This comes from the belief that better, more expensive, agents will usually produce better code than 5 cheaper agents running in parallel with some LLM judge to choose between or combine their outputs.

mejutoco• 1 year ago

Why would spinning containers remove the benefits? Presumably there is a terminal too interacting with the containers.

eru4• 1 year ago

Nah, if parallelism will help, it'll be abstracted away from the user.

ldjkfkdsjnv• 1 year ago

as the models get better, IDEs will be seen as low level

magackame• 1 year ago

Wait you write your code by hand??? ewww...

mountainriver3• 1 year ago

What??? It’s literally the worst interface

Do you not want to edit your code after it’s generated?

aaronbrethorst• 1 year ago

Sure, in VS Code. Or Xcode. Or IntelliJ/GoLand/RubyMine.

handfuloflight6• 1 year ago

...if your IDE doesn't have a terminal then it isn't an IDE.

bretpiatt• 1 year ago

I'm running terminal in one window with AI interaction and then VS Code with project on same directories so I can see via color coding updated or new files to review in the IDE.

How do you interact with your projects?

ed_mercer• 1 year ago

Exactly. It has access to literally everything including any MCP server. It's so awesome having claude code check my database using a read-only user, or have it open a puppeteer browser and check whether its CSS changes look weird or not. It's the perfect interface and anthropic nailed it.

It can even debug my k8s cluster using kubectl commands and check prometheus over the API, how awesome is this?

leptons4• 1 year ago

or have it open a puppeteer browser and check whether its CSS changes look weird or not.

It's got 7 fingers? Looks fine to me! - AI

bionhoward• 1 year ago

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

alwa• 1 year ago

I can’t speak for their legal department, but their product, Claude Code, bears signs of lavish attention to detail. Right down to running Haiku on the context to come up with cute appropriate verbs for the “working…” indicators.

konexis007• 1 year ago

jilles• 1 year ago

How does this compare with Apples or Orange?

brcmthrowaway• 1 year ago

How does this compare with Code::Blocks?

blahgeek• 1 year ago

Asking it to explain rust borrow checker is one of the worst examples to demonstrate its ability to read code. There are piles of that in its training data.

dundarious• 1 year ago

Agreed, ask it to explain how exceptions are handled in python asyncio tasks, even given all the code, and it will vacillate like the worst intern in the world. What's more, there's no way to "teach" it, and even if there was, it would not last beyond the current context.

A complete waste of time for important but relatively simple tasks.

gilbetron• 1 year ago

"There are piles of that in its training data"

Such a weird complaint. If you were to explain the rust borrow checker to me, should I complain that it doesn't count because you had read explanations of the borrow checker? That it was "in your training data"? I mean, do you think you just understand the borrow checker without being taught about it in some form?

I mean, I get what you are kind of saying, that there isn't much evidence that they tools are able to generate new ideas, and that the sheer amount of knowledge it has obscures the detection of that phenomenon, but practically speaking I don't care because it is useful and helpful (within its hallucinatory framework).

dirtbag__dad• 1 year ago

This article is inspiring. I haven’t had the moment to get my head out of the Cursor + biz logic water until now. Very cool to think about LLMs automagically creating changelogs, testing packaging when dependencies are bumped, forcing unit tests on features.

Is anyone aware of something like this? Maybe in the GitHub actions or pre-commit world?

pjm3312• 1 year ago

https://docs.anthropic.com/en/docs/claude-code/github-action...

citizenpaul2• 1 year ago

automagically creating changelogs, testing packaging when dependencies are bumped, forcing unit tests on features.

Yeah now companies that paid lip service to those things can still not have them but pretend they do cause the AI did it....

rbren• 1 year ago

I’m biased [0], but I think we should be scripting around LLM-agnostic open source agents. This technology is changing software development at its foundations—-we need to ensure we continue to control how we work.

[0] https://github.com/all-hands-ai/openhands

ProofHouse• 1 year ago

This 10000%

handfuloflight6• 1 year ago

But what do we do if the closed models are just better?

davidmurdoch• 1 year ago

Wait?

bluefirebrand• 1 year ago

Steal from them shamelessly, the same way they stole from everyone else?

rkangel• 1 year ago

The agents are separate from the models. Claude Code only allows you to use Claude, but Aider allows you to use any model.

robotbikes• 1 year ago

This looks like a good resource. There are some pretty powerful models that will run on a Nvidia 4090 w/ 24gb of RAM. Devstral and Queen 3. Ollama makes it simple to run them on your own hardware, but the cost of the GPU is a significant investment. But if you are paying $250 a month for a proprietary tool it would pay for itself pretty quickly.

seanmcdirmid• 1 year ago

A Max M3 with 64 GB works well for a wider range of models although it fairs worse on stable diffusion jobs. Plus you can get it as a laptop.

NitpickLawyer• 1 year ago

There are some pretty powerful models that will run on a Nvidia 4090 w/ 24gb of RAM. Devstral and Queen 3.

I'd caution against using devstral on a 24 gb vram budget. Heavy quantisation (the only way to make it fit into 24gb) will affect it a lot. Lots of reports on locallama about subpar results, especially from kv cache quant.

We've had good experiences with running it fp8 and full cache, but going lower than that will impact the quality a lot.

mjrbrennan2• 1 year ago

Not trying to be rude here, but that `last_week.md` is horrible to me. I can't imagine having to read that let alone listen to the computer say it to me. It's so much blah blah and fluff that reads like a bad PR piece. I'd much rather scan through commits of the last week.

I've found this generally with AI summaries...usually their writing style is terrible, and I feel like I cannot really trust them to get the facts right, and reading the original text is often faster and better.

fullstackchris3• 1 year ago

Yeah I was done at "What happened here was more than just code..." -_-

jsjohnst2• 1 year ago

You got past the grey text on gray background? -_-

block_dagger• 1 year ago

You can specify desired style in the prompt. The author seems to like PR sounding fluff while making morning coffee.

WD-423• 1 year ago

I felt the same thing about the onboarding. Like what future are we trying to build for ourselves here, exactly? The kind where instead of sitting down with a coworker to learn about a codebase, instead we get an ai generated PowerPoint to read alone????

Im so over this timeline.

JohnMakin2• 1 year ago

all of this just reads like the supposed UML zeitgeist that was supposed to transform java and eliminate development 20 years ago

if this is all ultimately java but with even more steps, its a sign im definitely getting old. it’s just the same pattern of non technical people deceiving themselves into believing they dont need to be technical to build tech and then ultimately resulting in again 10-20 years of re-learning the painful lessons of that.

let me off this train too im tired already

mjrbrennan2• 1 year ago

Yes that's what gets me too. I want to engage with my coworkers, you know other humans? And get their ideas and input and summaries. Not just sit in my office alone having the computer explain everything to me badly, or read through Powerpoints of all things...

crucialfelix• 1 year ago

Usually the tricks and problems in a codebase are not in the codebase at all, they are in somebody's head.

It would be helpful if I had a long rambling dialogue with a chat model and it distilled that.

CuriouslyC2• 1 year ago

Naw, the new future (technically the present for orgs that use AI intelligently) is:

The AI already generated comprehensive README.md files and detailed module/function/variable (as needed) doc comments, which you could read but end up mostly being consumed by another AI, so you can just tell it what you're trying to do and ask it how you might accomplish that in the codebase, first at a conceptual level, then in code once you feel comfortable enough with the system to be able to validate the work.

All the while you're sitting next to another coworker who's also doing the same thing, while you talk about high level architecture stuff, make jokes, and generally have a good time. Shit, I don't even mind open offices as much as I used to, because you don't need that intense focus to get into a groove to produce code quickly like you did when manually writing it, so you can actually have conversations with an entire table of coworkers and still be super productive.

No comment on the political/climate side of this timeline, but the AI part is pretty good when you master it.

never_inline3• 1 year ago

Here's a system prompt I tend to use

    ## Instructions
    * Be concise
    * Use simple sentences. But feel free to use technical jargon.
    * Do NOT overexplain basic concepts. Assume the user is technically proficient.
    * AVOID flattering, corporate-ish or marketing language. Maintain a neutral viewpoint.
    * AVOID vague and / or generic claims which may seem correct but are not substantiated by the the context.

Cannot completely avoid hallucinations and it's good to avoid AI for text that's used for human-to-human communication. But this makes AI answers to coding and technical questions easier to read.

NewsaHackO• 1 year ago

it's good to avoid AI for text that's used for human-to-human communication.

Assuming it is fact checked, why?

TZubiri• 1 year ago

Remember the sycophant bug? Maybe making the user FEELGOOD is part of what makes it feel smart or like a good experience. Is the reward function being smart? Is it maximizing interaction? Does it conflict with being accurate?

joshstrange• 1 year ago

I ran the prompt as-is on one of the main repos that I work on and the sycophancy was cloying.

It praised so many things that I would just consider table steaks and made simple tweaks or features sound like massive projects.

I’m sure it could be improved by tweaking the prompt and there were parts of it that I found impressive that it had picked out (specifically things not in commit messages) but I found it unusable in its current form.

beigebrucewayne3• 1 year ago

I agree, it's atrocious!

1. I shouldn't have used a newly created repo that had no real work over the course of the last week.

2. I should have put more time into the prompt to make it sound less nails on chalkboard.

TeMPOraL13• 1 year ago

If this was meant to be read, I might've agreed, but:

1) This was supposed to be piped through TTS and listened to in the background, and...

2) People like podcasts.

Your typical podcast is much worse than this. It's "blah blah" and "hahaha <interaction>" and "ooh <emoting>" and "<irrelevant anecdote>" and "<turning facts upside down and injecting a lie for humorous effect>", and maybe some of the actual topic mixed in between, and yet for some reason, people love it.

I honestly doubt this specific thing would be useful for me, but I'm not going to assume it's plain dumb, because again, podcasts are worse, and people love it.

xandrius2• 1 year ago

What kind of podcast have you listened to, if any?

They aren't all Joe Rogan.

rsynnott3• 1 year ago

Yeah, I honestly don't know how anyone can put up with reading this sort of thing, much less have it read to them by a computer(!)

I suppose preferences differ, but really, does anyone _like_ this sort of writing style?

fennecfoxy3• 1 year ago

Yup, you can always tell LLMs just from the ridiculous output most of the time. Like 8-20 sentences minimum, for the most basic thing.

Even Gemini/gpt4o/etc are all guilty of this. Maybe they'll tighten things up at some point - if I ask an assistant a simple question like "is it possible to put apples into a pie?" what I want is "Yes, it is possible to put apples into a pie. Would you like to know more?"

But not "Yes, absolutely — putting apples into a pie is not only possible, it's classic! Apple pie is one of the most well-known and traditional fruit pies. Typically, sliced apples are mixed with sugar, cinnamon, nutmeg, and sometimes lemon juice or flour, then baked inside a buttery crust. You can use various types of apples depending on the flavor and texture you want (like Granny Smith for tartness or Honeycrisp for sweetness). Would you like a recipe or tips on which apples work best?" (from gpt4).

ozim• 1 year ago

Python, a journey that began with an initial commit and evolved through a series of careful refinements to establish a robust foundation for the project..

Wow yeah what a waste. That is exactly the opposite of saving time.

aussieguy1234• 1 year ago

I played around with agents yesterday, now I'm hooked.

I got Claude Code (With CLine and VSCode) to do a task for a personal project. It did it about 5x faster than i'd have been able to do manually including running bash commands e.g. to install dependencies for new npm packages.

These things can do real work. If you have things in plain text format like markdown, csv spreadsheets etc, alot of what normal human employees do today could be somewhat automated.

You currently still need a human to supervise the agent and what its doing, but that won't be needed anymore in the not so distant future.

johnwheeler• 1 year ago

I've actually stumbled upon a novel new way of using Claude code that I don't think anybody else is doing that's insanely better. I'll release it soon.

throwawayoldie3• 1 year ago

"...but the proof is too large to fit in this margin."

tom_m• 1 year ago

Well, there will always be a job for programmers folks.

fullstackchris3• 1 year ago

Gonna be a bit blunt here and ask why hooking up an agentic CLI tool to one or more other software tool(s) is the top post on HN right now... sure, some of these ideas are interesting but at the end of the day literally all of them have been explored / revisited by various MCP tools (or can be done more or less in scripted / hacked ways as the author shows here)

I don't know, just feels like a weird community response to something that is the equivalent to me of bash piping...

AstroBen2• 1 year ago

Side note but the contrast between background and text here makes this really hard to read

jsjohnst2• 1 year ago

You aren’t missing much if you just skip it

thunkle• 1 year ago

For me it's the blinking cursor at the top... It's hard to focus on the text.

jvanderbot3• 1 year ago

I can't wait until Section 174 changes are repealed and nobody is financially invested in software from AI anymore.

tra3• 1 year ago

Thank you, finally a realistic take.

jvanderbot3• 1 year ago

It seems I'm in the vast minority. Post hoc ergo proper hoc indeed.

eru4• 1 year ago

America = world?

jvanderbot3• 1 year ago

Is this meant to say "I don't care because I'm not in USA"? Or "it's not a problem because it's only USA?" Or "don't speak of US-specific situations on this forum because it contains people of many nationalities?"

It's entirely possible for a world changing tech to be created and steered to match a unique problem inside one country, and for that to change job markets everywhere.

distortionfield• 1 year ago

Unrelated; but I am absolutely in love with this blog theme and color scheme.

dweinus• 1 year ago

Is it Shakespeare? No.

It's at least decent though, right?

"What emerged over these seven days was more than just code..."

Yeesh, ok, but is it accurate?

Over time this will likely degrade the performance and truthfulness

Sure, but it's cheap right?

$250 a month.

Well at least it's not horrible for the environment and built on top of massive copyright violations, right?

Right?

citizenpaul2• 1 year ago

openai codex (soon to be rewritten in rust)

Lol, I guess their AI is too good for a redactor. Better have humans do it.

Syzygies• 1 year ago

No mention of Opus there or here (so far).

Having tried everything I settled on a $100/month Anthropic "Max" plan to use Claude Code. Then I learned how Claude Opus 4 is currently their best but most expensive model for my situation (math code and research). I limited out of a five hour session, switched to their API, and burned $20 in an hour. So I upgraded to $200/month "Max" and haven't hit limits yet.

Models matter. All these stories are like "I met a person who wasn't that smart." Duh!

beigebrucewayne3• 1 year ago

All of this was with Opus.

luckystarr• 1 year ago

I recently investigated some problematic behaviour of both Opus 4 and Sonnet 4. When tasked to develop something more complicated (broker fed task management system, staggered execution scheduler) they would inevitably produce thousands of lines of over engineered, unmaintainable garbage. When Opus was then tasked to simplify it it boiled it down to 300 lines in one shot. The result was brilliant. This happened twice.

Moral of the story: I found out that I didn't constrain them enough. I now insist that they keep the core logic to a certain size (e.g. 300 lines) and not produce code objects for each concept but rather "fold them into the code".

This improved the output tremendously.

jumski2• 1 year ago

Great article! I have similar observations and techniques and Claude Code is exceptionally good - most of the days I'm working on multiple things at once (thanks to git worktrees) and each going faster than ever - that's really crazy.

For the "sub agents"thing, I must admit, that Claude Code calling o3 via sigoden/aichat saved me countless of times!

There are just issues that o3 excells at (race conditions, bug hunting - anything that requires lot of context and really high reasoning abilities).

But I'm using it less since Opus 4 came out. And of course its none of the sub-agent thing at all.

I use this prompt @included in the main CLAUDE.md: https://github.com/pgflow-dev/pgflow/blob/main/.claude/advan...

sigoden/aichat: https://github.com/sigoden/aichat

_1tem• 1 year ago

wait what? how do you work on multiple things at once with git worktrees?

pjm3312• 1 year ago

I never had any reason to use it before claude code et al. So I also wasn’t aware

Commands for working with copies of your entire repo in a new folder on a new branch

https://git-scm.com/docs/git-worktree

jumski2• 1 year ago

git worktree uses one repo to laid out multiple branches in separate directories.

git worktree add new/path/for/worktree branchname

I now refuse to use git checkout to switch branches, always keep my main branch checked out and updated and always use worktrees to work on features. Love this workflow!

rikschennink• 1 year ago

I tried to read this on mobile but the blinking cursor makes it impossible.

beigebrucewayne3• 1 year ago

Removed it! I agree it was distracting.

hoppp• 1 year ago

First time I heard about marp, very handy tool

Snorting the AGI with Claude Code

Related Stories