Comment by austinbaggio
16 hours ago
Which of the 1000 is your favorite? There does seem to be a shallow race to optimizing xyz benchmark for some narrow sliver of the context problem, but you're right, context problem space is big, so I don't think we'll hurry to join that narrow race.
| Which of the 1000 is your favorite?
None, that's what I'm trying to say. My favorite is just storing project context locally in docs that agents can discover on their own or I can point to if needed. This doesn't require me to upload sensitive code or information to anonymous people's side projects and has and equivalent amount of hard evidence for efficacy (zero), but at least has my own anecdotal evidence of helping and doesn't invite additonal security risk.
People go way overboard with MCPs and armies of subagents built on wishes and unproven memory systems because no one really knows for sure how to get past the spot we all hit where the agentic project that was progressing perfectly hits a sharp downtrend in progress. Doesn't mean it's time to send our data to strangers.
> no one really knows for sure how to get past the spot we all hit where the agentic project that was progressing perfectly hits a sharp downtrend in progress.
FWIW, I find this eventual degradation point comes much later and with fewer consequences when there are strict guardrails inside and outside of the LLM itself.
From what I've seen, most people try to fix only the "inside" part - by tweaking the prompts, installing 500 MCPs (that ironically pollute the context and make problem worse), yell in uppercase in hopes that it will remember etc, and ignore that automated compliance checks existed way before LLMs.
Throw the strictest and most masochistic linting rules at it in a language that is masochistic itself (e.g. rust), add tons of integration tests that encode intent, add a stop hook in CC that runs all these checks and you've got a system that is simply not allowed to silently drift and can put itself back on track with feedback it gets from it.
Basically, rather than trying to hypnotize an agent to remember everything by writing a 5000 line agents.md, just let the code itself scream at it and feed the context.
Wait.