Hacker News new | ask | show | jobs
by ericmcer 262 days ago
It seems possible for openAI/Anthropic to rework their tools so they discard/add relevant context on the fly, but it might have some unintended behaviors.

The main thing is people have already integrated AI into their workflows so the "right" way for the LLM to work is the way people expect it to. For now I expect to start multiple fresh contexts while solving a single problem until I can setup a context that gets the result I want. Changing this behavior might mess me up.
2 comments
vel0city 262 days ago
A number of agentic coding tools do this. Upon an initial request for a larger set of actions, it will write a markdown file with its "thoughts" on its plan to do something, and keep notes as it goes. They'll then automatically compact their contexts and re-read their notes to keep "focused" while still having a bit of insight on what it did previously and what the original ask was.
link
cvzakharchenko 262 days ago
Interesting. I know people do this manually. But are there agentic coding tools that actually automate this approach?
link
sshine 262 days ago
Claude Code has /init and /compact that do this. It doesn’t recreate the context as-is, but creates a context that is presumed to be functionally equivalent. I find that’s not the case and that building up from very little stored context and a lot of specialised dialogue works better.
link
vel0city 262 days ago
I've seen this behavior with Cursor, Windsurf, and Amazon Q. It normally only does it for very large requests from what I've seen.
link
tom_m 260 days ago
This does help, yes. Todo lists are important. They also reinforce order of operations.
link
sshine 262 days ago
> rework their tools so they discard/add relevant context on the fly

That may be the foundation for an innovation step in model providers. But you can achieve a poor man’s simulation if you can determine, in retrospect, when a context was at peak for taking turns, and when it got too rigid, or too many tokens were spent, and then simply replay the context up until that point.

I don’t know if evaluating when a context is worth duplicating is a thing; it’s not deterministic, and it depends on enforcing a certain workflow.

link