It is a lot like giving a person instructions, the more you tell them, the more they will forget the specifics.
Don't trust large context windows
71–80 of 211 posts
Re: Don't trust large context windows
#72Re: Don't trust large context windows
#73I'm actually doing a big refactoring in a project where if everything gets loaded (code / docs), the context gets like 750k filled (Opus 4.8), and then the agent has the remaining ~200k to do actual coding, until I have to reset. I haven't finished the work but I'm like 80% there, and it seems the progress is good and the quality is also good, verified by doing some performance tests and a lot of comparisons between outputs between the original code and the new one.
Maybe I could achieve better and quicker results with keeping the context in the proper zone, but trying it will have to wait until the next project.
Re: Don't trust large context windows
#74I'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…
This makes intuitive sense. Can I ask what harness you're using that allows you to configure the constraint and how?
Re: Don't trust large context windows
#75Why is it surprising that, at some point, more information will lead to worse performance?
It seems obvious. Moreover, in a simple model, it seems like whatever tokens you do add have to have MORE information than the average in the existing window.
In a non-trivial model (and this is the model I would choose), since you are adding them to the end, they likely have to have MUCH more information.
Proof as always is an exercise to the reader.
Re: Don't trust large context windows
#76aka Softmax context rot
Re: Don't trust large context windows
#77> The number on the box gets bigger every release.
Not really tho right? Since we got to 1m context in mid 2025 nearly no one has gone higher.
Re: Don't trust large context windows
#78Opus in recent versions is fine beyond 100k, but I usually do try to keep it under 200k. But, this is also why so-called "memory" systems are usually a mistake that make the models dumber. They don't have memory, they only have context, and every irrelevant fact you shove into the context is less context for the problem. Less distractions, better results. The way to have the agent remember things is to have it docume…
At least for me, Opus keeps writing stuff to memories, only to consistently forget checking those memories before doing the same mistake again. This ("remember to check memories!") is of course then again written as a memory... Clearly not a very well working system, yep.
Yeah, I see it write stuff to memory pretty regularly, maybe it works sometimes, but for things I want it to stop doing or always do, I make it impossible to do otherwise via lint or some style enforcement, or via a test that fails if code shows up that violates the constraint.
But, it does a good job following existing conventions in a codebase, as long as they're really consistent. So the more actively you enforce that consistency the more likely it is to do the right thing without memories or prompting.
I don't like "never do" or "always do" type rules in AGENTS.md or in memory, as it often over-interprets them and ties itself in knots trying to satisfy an impossible set of goals.
Re: Don't trust large context windows
#79I'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…
This is interesting to me because reducing context & token usage is in the user's best interest but not in the financial interest of AI vendors. I am not an expert but it sounds like your "one simple trick" would fix context issues and allow much tighter control over token usage. Thanks for being willing to share this tip in an HN comment, changing how those in the know use AI agents going forward -- it's hard to keep up!
Re: Don't trust large context windows
#80Earlier quoted context omitted.
It is the other way round. In an interactive session, adding "Fine, but make the button red" after the model generated a first solution more than doubles the tokens used. As the model now not only gets the original code and the feature request but also the updated code plus the change request as input tokens. Sending a feature request to an LLM and then sending the feature request again with "The button shall be red"…
"Make the button red" probably doesn't need an LLM at all.
One tends to use LLMs for everything in practice. It‘s inconvenient to switch mode of operation