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

Don't trust large context windows

garrit.xyz

Post reply on HN
Print view View original

161–170 of 211 posts

Re: Don't trust large context windows

#161

Post by benashford »

dofm wrote: post #123

I guess I am mostly enjoying learning the fundamentals of AI stuff, even though I disagree with the direction it is going. But I am struggling to put into words how alarming I find the comments on threads like this — all sorts of good-natured anecdotes about how XYZ works for them that are more like the suggestions in pet care or cookery threads on Facebook. (Or worse still, like any Facebook 3D printing group: anyon…

> Any shared sense of rigour is just completely torpedoed by the LLM world, particularly the cloud LLM world it seems, and we are reduced to cargo culting. Nobody is any more right or wrong than anyone else.

There was always some of this in the tech world, long before LLMs came along.

I've sat in so many meetings when decisions were made based on "that's what _slightly more prestigious company_ does" rather than objective measurable criteria. (And the evidence that the thing in question wasn't universally followed by _slightly more prestigious company_ carried surprisingly little weight).

Re: Don't trust large context windows

#162

Post by claw-el »

dofm wrote: post #123

I guess I am mostly enjoying learning the fundamentals of AI stuff, even though I disagree with the direction it is going. But I am struggling to put into words how alarming I find the comments on threads like this — all sorts of good-natured anecdotes about how XYZ works for them that are more like the suggestions in pet care or cookery threads on Facebook. (Or worse still, like any Facebook 3D printing group: anyon…

This lack of rigour feels a lot like “did you try restarting the computer? Most of the time, others tried restarting the computer and it works”

Re: Don't trust large context windows

#164

Post by hadlock »

bob1029 wrote: post #152
gbro3n wrote: post #74

Earlier quoted context omitted.

This makes intuitive sense. Can I ask what harness you're using that allows you to configure the constraint and how?

It's a custom agent loop. There are no other parties involved here. Just vanilla C#/.NET and the OpenAI DLL.

Are you going to open source it

Re: Don't trust large context windows

#166

Post by skybrian »

darkwater wrote: post #155
dofm wrote: post #123

I guess I am mostly enjoying learning the fundamentals of AI stuff, even though I disagree with the direction it is going. But I am struggling to put into words how alarming I find the comments on threads like this — all sorts of good-natured anecdotes about how XYZ works for them that are more like the suggestions in pet care or cookery threads on Facebook. (Or worse still, like any Facebook 3D printing group: anyon…

What sense of rigour is going to be in a field (LLM usage as a user) where models, context sizes, tooling and broadly "rules" (scary quotes) change every few weeks? There is no literal change to have a scientific approach to anything, churn is too high, there are papers about model XYZ v 12345 from a few months ago that are already old because there is model ABC on version 54321 that addresses half of the issue shown…

With benchmarks, you can re-run them after a change. A measurement in a paper will go out of date quickly unless turned into a benchmark.

Re: Don't trust large context windows

#167

Post by dofm »

benashford wrote: post #161
dofm wrote: post #123

I guess I am mostly enjoying learning the fundamentals of AI stuff, even though I disagree with the direction it is going. But I am struggling to put into words how alarming I find the comments on threads like this — all sorts of good-natured anecdotes about how XYZ works for them that are more like the suggestions in pet care or cookery threads on Facebook. (Or worse still, like any Facebook 3D printing group: anyon…

> Any shared sense of rigour is just completely torpedoed by the LLM world, particularly the cloud LLM world it seems, and we are reduced to cargo culting. Nobody is any more right or wrong than anyone else. There was always some of this in the tech world, long before LLMs came along. I've sat in so many meetings when decisions were made based on "that's what _slightly more prestigious company_ does" rather than obje…

Absolutely I agree there has always been some cargo culting going on; that's true of all process-oriented businesses.

But people are now individually acting this way on their desks on an hour by hour basis. LLMs make cargo-culting inevitable because they are inscrutable and opaque.

There is always this sense in the LLM-proponent world that LLMs are at any moment as bad as they are ever going to be; line goes up.

But it seems clear that the gap between perceived and measurable productivity is still likely spent in poking entrails with a stick.

We are so used to probabilistic tools that have significant setup time before they become valuable and save us loads of time that we're at risk of repeatedly writing off that setup time without seeing the rewards, believing that one day it will actually work out that way.

(Which is most recognisable from the early JS frontend frameworks era.)

Meantime here we have an article that shows that a thing (longer context windows) that people thought would functionally solve a problem so we would get the value from all that setup does not, in fact, very meaningfully kick it down the road, and the comments are still full of entrails-and-stick work.

Re: Don't trust large context windows

#168

Post by wrs »

KronisLV wrote: post #81
bob1029 wrote: post #40

I've been able to avoid context size issues by applying one simple constraint to my agent loop. What I do is prevent all tool calling in the user's top-level conversation thread. Anything that needs to tool call must happen in a recursive invoke of the agent, which returns whatever results to caller. I can keep the same high level conversation going for an entire day over a million LOC+ codebase without ever hitting…

For anyone using Claude Code, ask it to do all the work in workflows (it has a tool for that), they released that feature together with Opus 4.8 and it also seems a bit better at doing long tasks as well. The main conversation just orchestrates the work at that point.

You can also just ask it to do work in a subagent. It will write a plan and launch the subagent to do the actual code, keeping it out of the main context.

In addition, you can co-author a plan for a biggish chunk of work, divided into stages, have it launch a subagent for phase 1 and check its work, then ESC-ESC to go back to just after you wrote the plan and have it do phase 2. Repeat until done. This keeps the overall goal in the main context for the review, but clears out previous reviews. Kind of like a workflow but with more control.

Re: Don't trust large context windows

#169

Post by andai »

bob1029 wrote: post #40

I've been able to avoid context size issues by applying one simple constraint to my agent loop. What I do is prevent all tool calling in the user's top-level conversation thread. Anything that needs to tool call must happen in a recursive invoke of the agent, which returns whatever results to caller. I can keep the same high level conversation going for an entire day over a million LOC+ codebase without ever hitting…

So what does the top level thread look like? "Make foo() do bar" (Subagent invoked) "Job finished!"

Re: Don't trust large context windows

#170

Post by conditionnumber »

dofm wrote: post #123

I guess I am mostly enjoying learning the fundamentals of AI stuff, even though I disagree with the direction it is going. But I am struggling to put into words how alarming I find the comments on threads like this — all sorts of good-natured anecdotes about how XYZ works for them that are more like the suggestions in pet care or cookery threads on Facebook. (Or worse still, like any Facebook 3D printing group: anyon…

It's not just you! Here's a lovely quote from an influential paper, "We offer no explanation as to why these architectures seem to work; we attribute their success, as all else, to divine benevolence." I think people went through a similar phase with steam engines. Lot's of practical engineering and heuristics to explain what works, before the emergence of a solid theoretical foundation (thermodynamics) to explain why.

https://arxiv.org/pdf/2002.05202

Post reply on HN