If you are truly bitter-lesson pilled - give the agent all the tools and let it decide which to use. - regex (grep) - hybrid search (bm25+vector) this X vs Y is uninteresting when the answer can be both.
I'm still disappointed that ai can't use ctags, its used for finding strings and patterns, its right there.
> I'm still disappointed that ai can't use ctags,
What do you mean by this? Do you mean not automatically build the index?
If you are truly bitter-lesson pilled - give the agent all the tools and let it decide which to use. - regex (grep) - hybrid search (bm25+vector) this X vs Y is uninteresting when the answer can be both.
it will only use tools it was trained on? what's the benfit of givig it all the tools.
If you are truly bitter-lesson pilled - give the agent all the tools and let it decide which to use. - regex (grep) - hybrid search (bm25+vector) this X vs Y is uninteresting when the answer can be both.
Exactly this, and this tool called qmd is what I use for the hybrid search portion. It also uses local LLMs to provide summaries on your own markdown data too. My agents use both depending on what type of search they are doing, and both provide good results.
Tangential, I have a hook that rewriters grep to rg but lately I wonder if this is actually wasteful as the model is so biased to grep, is there a way to shim/alias perhaps?
I've been on a look out for any harness that properly secures a protocol to the LLM, but they're all just "here's some tools, hopefully you don't use bash for everything".
If you are truly bitter-lesson pilled - give the agent all the tools and let it decide which to use. - regex (grep) - hybrid search (bm25+vector) this X vs Y is uninteresting when the answer can be both.
That assumes that the agent knows which one is better. And to bake in which one is better via post-training would require a study like this to establish where each one works well
I’ve got a custom ultra high performance streaming semantic search I exposed as a tool and the RL bias in Claude is almost insurmountable without copious and consistent steering. Codex will follow instructions and use the tools I ask it to but for gods sake between Claude asking to take a nap because it’s getting late in the session and it regressing to RL biased tools like grep it’s maddening. When I can get it to use my compositional tools tool calls drop from like 20-50 to 3-4, but it’s almost impossible to steer.
Many harnesses are doing this already, "Grep" is the tool name, ripgrep is the implementation It depends on if it is using Grep the harness tool or Grep from the bash tool
I see it using the Bash tool infrequently though sometimes Grep. I'm on Claude Code for now due to subscription lock-in, been contemplating moving to pi though
Why do you have subscription lock-in? Even if you pay for a yearly subscription, Anthropic will refund you pro rata if you cancel early.