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

Context is the bottleneck for coding agents now

runnercode.com

Post reply on HN
Print view View original

101–110 of 193 posts

Re: Context is the bottleneck for coding agents now

#101

Post by alchemist1e9 »

reclusive-sky wrote: post #79
asdev wrote: post #41

I don't think intelligence is increasing. Arbitrary benchmarks don't reflect real world usage. Even with all the context it could possibly have, these models still miss/hallucinate things. Doesn't make them useless, but saying context is the bottleneck is incorrect.

I agree, I often see Opus 4.1 and GPT5 (Thinking) make astoundingly stupid decisions with full confidence, even on trivial tasks requiring minimal context. Assuming they would make better decisions "if only they had more context" is a fallacy

Is there a good example you could provide of that? I just haven’t seen that personally so I’d be interested in any examples on these current models. I’m sure we all remember in the early days lots of examples of stupidity being posted and it was interesting. It be great if people kept doing that so we could get a better sense of which types of problems they are failing with astounding levels of stupidity on.

Re: Context is the bottleneck for coding agents now

#102

Post by chankstein38 »

asdev wrote: post #41

I don't think intelligence is increasing. Arbitrary benchmarks don't reflect real world usage. Even with all the context it could possibly have, these models still miss/hallucinate things. Doesn't make them useless, but saying context is the bottleneck is incorrect.

Agreed. I feel like, in the case of GPT models, 4o was better in most ways than 5 has been. I'm not seeing increases in quality of anything between the two 5 feels like a major letdown honestly. I am constantly reminding it what we're doing lol

Re: Context is the bottleneck for coding agents now

#103

Post by tptacek »

simonw wrote: post #99
tptacek wrote: post #94

Earlier quoted context omitted.

Asking, not arguing, but: why can't they? You can give an agent access to its own context and ask it to lobotomize itself like Eternal Sunshine. I just did that with a log ingestion agent (broad search to get the lay of the land, which eats a huge chunk of the context window, then narrow searches for weird stuff it spots, then go back and zap the big log search). I assume this is a normal approach, since someone else…

This is also the idea behind sub-agents. Claude Code answers questions about things like "where is the code that does X" by firing up a separate LLM running in a fresh context, posing it the question and having it answer back when it finds the answer. https://simonwillison.net/2025/Jun/2/claude-trace/

I'm playing with that too (everyone should write an agent; basic sub-agents are incredibly simple --- just tool calls that can make their own LLM calls, or even just a tool call that runs in its own context window). What I like about Eternal Sunshine is that the LLM can just make decisions about what context stuff matters and what doesn't, which is a problem that comes up a lot when you're looking at telemetry data.

Re: Context is the bottleneck for coding agents now

#104

Post by tra3 »

simonw wrote: post #99
tptacek wrote: post #94

Earlier quoted context omitted.

Asking, not arguing, but: why can't they? You can give an agent access to its own context and ask it to lobotomize itself like Eternal Sunshine. I just did that with a log ingestion agent (broad search to get the lay of the land, which eats a huge chunk of the context window, then narrow searches for weird stuff it spots, then go back and zap the big log search). I assume this is a normal approach, since someone else…

This is also the idea behind sub-agents. Claude Code answers questions about things like "where is the code that does X" by firing up a separate LLM running in a fresh context, posing it the question and having it answer back when it finds the answer. https://simonwillison.net/2025/Jun/2/claude-trace/

I keep wondering if we're forgetting the fundamentals:

> Everyone knows that debugging is twice as hard as writing a program in the first place. So if you’re as clever as you can be when you write it, how will you ever debug it?

https://www.laws-of-software.com/laws/kernighan/

Sure, you eat the elephant one bite at a time, and recursion is a thing but I wonder where the tipping point here is.

Re: Context is the bottleneck for coding agents now

#105

Post by jwpapi »

I’m really wondering why so many advertising posts mimicked as discourse make it to frontpage and I assume it’s a new Silicon Valley trick because there is no way HN community values these so much.

Let me tell you I’m scared of these tools. With Aider I have the most human in the loop possible each AI action is easy to undo, readable and manageable.

However even here most of the time I want AI to write a bulk of code I regret it later.

Most codebase challenges I have are infrastructural problems, where I need to reduce complexity to be able to safely add new functionality or reduce error likelihood. I’m talking solid well named abstractions.

This in the best case is not a lot of code. In general I would always rather try to have less code than more. Well named abstraction layers with good domain driven design is my goal.

When I think of switching to an AI first editor I get physical anxiety because it feels like it will destroy so many coders by leading to massive frustration.

I think still the best way of using ai is literally just chat with it about your codebase to make sure you have good practise.

Re: Context is the bottleneck for coding agents now

#106

Post by libraryofbabel »

tptacek wrote: post #94
aliljet wrote: post #14

There's a misunderstanding here broadly. Context could be infinite, but the real bottleneck is understanding intent late in a multi-step operation. A human can effectively discard or disregard prior information as the narrow window of focus moves to a new task, LLMs seem incredibly bad at this. Having more context, but leaving open an inability to effectively focus on the latest task is the real problem.

Asking, not arguing, but: why can't they? You can give an agent access to its own context and ask it to lobotomize itself like Eternal Sunshine. I just did that with a log ingestion agent (broad search to get the lay of the land, which eats a huge chunk of the context window, then narrow searches for weird stuff it spots, then go back and zap the big log search). I assume this is a normal approach, since someone else…

Yes! - and I wish this was easier to do with common coding agents like Claude Code. Currently you can kind of do it manually by copying the results of the context-busting search, rewinding history (Esc Esc) to remove the now-useless stuff, and then dropping in the results.

Of course, subagents are a good solution here, as another poster already pointed out. But it would be nice to have something more lightweight and automated, maybe just turning on a mode where the LLM is asked to throw things out according to its own judgement, if you know you're going to be doing work with a lot of context pollution.

Re: Context is the bottleneck for coding agents now

#107

Post by tptacek »

tra3 wrote: post #104
simonw wrote: post #99

Earlier quoted context omitted.

This is also the idea behind sub-agents. Claude Code answers questions about things like "where is the code that does X" by firing up a separate LLM running in a fresh context, posing it the question and having it answer back when it finds the answer. https://simonwillison.net/2025/Jun/2/claude-trace/

I keep wondering if we're forgetting the fundamentals: > Everyone knows that debugging is twice as hard as writing a program in the first place. So if you’re as clever as you can be when you write it, how will you ever debug it? https://www.laws-of-software.com/laws/kernighan/ Sure, you eat the elephant one bite at a time, and recursion is a thing but I wonder where the tipping point here is.

I think recursion is the wrong way to look at this, for what it's worth.

Re: Context is the bottleneck for coding agents now

#108

Post by tptacek »

libraryofbabel wrote: post #106
tptacek wrote: post #94

Earlier quoted context omitted.

Asking, not arguing, but: why can't they? You can give an agent access to its own context and ask it to lobotomize itself like Eternal Sunshine. I just did that with a log ingestion agent (broad search to get the lay of the land, which eats a huge chunk of the context window, then narrow searches for weird stuff it spots, then go back and zap the big log search). I assume this is a normal approach, since someone else…

Yes! - and I wish this was easier to do with common coding agents like Claude Code. Currently you can kind of do it manually by copying the results of the context-busting search, rewinding history (Esc Esc) to remove the now-useless stuff, and then dropping in the results. Of course, subagents are a good solution here, as another poster already pointed out. But it would be nice to have something more lightweight and…

This is why I'm writing my own agent code instead of using simonw's excellent tools or just using Claude; the most interesting decisions are in the structure of the LLM loop itself, not in how many random tools I can plug into it. It's an unbelievably small amount of code to get to the point of super-useful results; maybe like 1500 lines, including a TUI.

Re: Context is the bottleneck for coding agents now

#109

Post by cma »

bgirard wrote: post #31
aliljet wrote: post #14

There's a misunderstanding here broadly. Context could be infinite, but the real bottleneck is understanding intent late in a multi-step operation. A human can effectively discard or disregard prior information as the narrow window of focus moves to a new task, LLMs seem incredibly bad at this. Having more context, but leaving open an inability to effectively focus on the latest task is the real problem.

I think that's the real issue. If the LLM spends a lot of context investigating a bad solution and you redirect it, I notice it has trouble ignoring maybe 10K tokens of bad exploration context against my 10 line of 'No, don't do X, explore Y' instead.

Not that this shouldn't be fixed in the model, but you can jump to an earlier point in claude code and on web chat interfaces to get it out of the context, just sometimes you have other important stuff you don't want it to lose.
Post reply on HN