Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tools: Code Is All You Need

lucumr.pocoo.org

Post reply on HN
Print view View original

91–100 of 234 posts

Re: Tools: Code Is All You Need

#91

Post by pxc »

simonw wrote: post #74
nico wrote: post #73

Earlier quoted context omitted.

> LLM in a sandbox using tools in a loop, you can brute force that problem Does this require using big models through their APIs and spending a lot of tokens? Or can this be done either with local models (probably very slow), or with subscriptions like Claude Code with Pro (without hitting the rate/usage limits)? I saw the Mandelbrot experiment, it was very cool, but still a rather small project, not really comparabl…

The local models aren't quite good enough for this yet in my experience - the big hosted models (o3, Gemini 2.5, Claude 4) only just crossed the capability threshold for this to start working well. I think it's possible we'll see a local model that can do this well within the next few months though - it needs good tool calling, not an encyclopedic knowledge of the world. Might be possible to fit that in a model that…

There's a fine-tune of Qwen3 4B called "Jan Nano" that I started playing with yesterday, which is basically just fine-tuned to be more inclined to look things up via web searches than to answer them "off the dome". It's not good-good, but it does seem to have a much lower effective hallucination rate than other models of its size.

It seems like maybe similar approaches could be used for coding tasks, especially with tool calls for reading man pages, info pages, running `tldr`, specifically consulting Stack Overflow, etc. Some of the recent small MoE models from Chinese companies are significantly smarter than models like Qwen 4B, but run about as quickly, so maybe on systems with high RAM or high unified memory, even with middling GPUs, they could be genuinely useful for coding if they are made to be avoid doing anything without tool use.

Re: Tools: Code Is All You Need

#92

Post by kibwen »

whiplash451 wrote: post #32
pclowes wrote: post #5

Directionally I think this is right. Most LLM usage at scale tends to be filling the gaps between two hardened interfaces. The reliability comes not from the LLM inference and generation but the interfaces themselves only allowing certain configuration to work with them. LLM output is often coerced back into something more deterministic such as types, or DB primary keys. The value of the LLM is determined by how well…

Interesting take but too bearish on LLMs in my opinion. LLMs have already found large-scale usage (deep research, translation) which makes them more ubiquitous today than 3D printers ever will or could have been.

No, 3D printers are the backbone of modern physical prototyping. They're far more important to today's global economy than LLMs are, even if you don't have the vantage point to see it from your sector. That might change in the future, but snapping your fingers to wink LLMs out of existence would change essentially nothing about how the world works today; it would be a non-traumatic non-event. There just hasn't been time to integrate them into any essential processes.

Re: Tools: Code Is All You Need

#93

Post by chriswarbo »

mritchie712 wrote: post #2

> try completing a GitHub task with the GitHub MCP, then repeat it with the gh CLI tool. You'll almost certainly find the latter uses context far more efficiently and you get to your intended results quicker. This is spot on. I have a "devops" folder with a CLAUDE.md with bash commands for common tasks (e.g. find prod / staging logs with this integration ID). When I complete a novel task (e.g. count all the rows that…

I use a similar file, but just for myself (I've never used an LLM "agent"). I live in Emacs, but this is the only thing I use org-mode for: it lets me fold/unfold the sections, and I can press C-c C-c over any of the code snippets to execute it. Some of them are shell code, some of them are Emacs Lisp code which generates shell code, etc.

Re: Tools: Code Is All You Need

#94

Post by jangxx »

deadbabe wrote: post #88
jangxx wrote: post #60

Earlier quoted context omitted.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

If it’s not happening at the scale it was pitched, then it’s not happening.

This makes no sense, just because something didn't become as big as the hypemen said it would doesn't make the inventions or users of those inventions disappear.

Re: Tools: Code Is All You Need

#95

Post by benreesman »

rapind wrote: post #64
benreesman wrote: post #47

Earlier quoted context omitted.

What we call an LLM today (by which almost everyone means an autogressive language model from the Generative Pretrained Transformer family tree, and BERTs are still doing important eork, believe that) is actually an offshoot of neural machine translation. This isn't (intentionally at least) mere HN pedantry: they really do act like translation tools in a bunch of observable ways. And while they have recently crossed…

> There is a hole in the ground where something between 100 billion and a trillion dollars in the ground that so far has about 20B in revenue (not profit) going into it annually. This is a concern for me. I'm using claude-code daily and find it very useful, but I'm expecting the price to continue getting jacked up. I do want to support Anthropic, but they might eventually need to cross a price threshold where I bail.…

Vibe coding is nonsense, and its really kind of uncomfortable to realize that a bunch of people you had tons of respect for are either ignorant or dishonest/bought enough to say otherwise. There's a cold wind blowing and the bunker-building crowd, well let's just say I won't shed a tear.

You don't stock antibiotics and bullets in a survival compound because you think that's going to keep out a paperclip optimizer gone awry. You do that in the forlorn hope that when the guillotines come out that you'll be able to ride it out until the Nouveau Regime is in a negotiating mood. But they never are.

Re: Tools: Code Is All You Need

#96

Post by hk1337 »

pclowes wrote: post #5

Directionally I think this is right. Most LLM usage at scale tends to be filling the gaps between two hardened interfaces. The reliability comes not from the LLM inference and generation but the interfaces themselves only allowing certain configuration to work with them. LLM output is often coerced back into something more deterministic such as types, or DB primary keys. The value of the LLM is determined by how well…

> Directionally I think this is right.

We have a term at work we use called, "directionally accurate", when it's not entirely accurate but headed in the right direction.

Re: Tools: Code Is All You Need

#97

Post by JyB »

the_mitsuhiko wrote: post #83
JyB wrote: post #57

Earlier quoted context omitted.

Do you mean that some tools (MCP clients) pass all functions of all configured MCP servers in the initial prompt? If that's the case: I understand the knee-jerk reaction but if it works? Also what theoretically prevents altering the prompt chaining logic in these tools to only expose a condensed list of MCP servers, not their whole capabilities, and only inject details based on LLM outputs? Doesn't seem like an insur…

> Do you mean that some tools (MCP clients) pass all functions of all configured MCP servers in the initial prompt? Not just some, all. That's just how MCP works. > If that's the case: I understand the knee-jerk reaction but if it works? I would not be writing about this if it worked well. The data indicates that it worse significantly worse than not using MCP because of the context rot, and the low too utilization.

I guess I don't see the technical limitation. Seem like a protocol update issue.

Re: Tools: Code Is All You Need

#98

Post by nativeit »

giovannibonetti wrote: post #81
jangxx wrote: post #60

Earlier quoted context omitted.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

Drones and VR require significant upfront hardware investment, which curbs adoption. On the other hand, adopting LLM-as-a-service has none of these costs, so no wonder so many companies are getting involved with it so quickly.

Right, but abstract costs are still costs to someone, so how far does that go before mass adoption turns into a mass liability for whomever is ultimately on the hook? It seems like there is this extremely risky wager that everyone is playing--that LLM's will find their "killer app" before the real costs of maintaining them becomes too much to bear. I don't think these kinds of bets often pay off. The opposite actually, I think every truly revolutionary technological advance in the contemporary timeframe has arisen out of its very obvious killer app(s), they were in a sense inevitable. Speculative tech--the blockchain being one of the more salient and frequently tapped examples--tends to work in pretty clear bubbles, in my estimation. I've not yet been convinced this one is any different, aside from the absurd scale at which it has been cynically sold as the biggest thing since Gutenberg, but while that makes it somewhat distinct, it's still a rather poor argument against it being a bubble.

Re: Tools: Code Is All You Need

#99

Post by falcor84 »

deadbabe wrote: post #88
jangxx wrote: post #60

Earlier quoted context omitted.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

If it’s not happening at the scale it was pitched, then it’s not happening.

Considering what we've been seeing in the Russia-Ukraine and Iran-Israel wars, drones are definitely happening at scale. For better or for worse, I expect worldwide production of drones to greatly expand over the coming years.

Re: Tools: Code Is All You Need

#100

Post by nativeit »

whiplash451 wrote: post #32
pclowes wrote: post #5

Directionally I think this is right. Most LLM usage at scale tends to be filling the gaps between two hardened interfaces. The reliability comes not from the LLM inference and generation but the interfaces themselves only allowing certain configuration to work with them. LLM output is often coerced back into something more deterministic such as types, or DB primary keys. The value of the LLM is determined by how well…

Interesting take but too bearish on LLMs in my opinion. LLMs have already found large-scale usage (deep research, translation) which makes them more ubiquitous today than 3D printers ever will or could have been.

[citation needed]
Post reply on HN