61–70 of 73 posts
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.
And a lot more tokens, and slower speed. Yes you can get more accuracy if you suck tons more data into context.
But compare this to more advanced code agent methods like Tree Sitter, PageRank, LSP, that build semantic maps to provide more relevant context. Grep alone can't do that
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".
It seems ridiculous that, for example, Copilot running in Visual Studio working on a C# codebase finds stuff in code by grepping around instead of using the Roslyn-driven code symbol and semantic database built into Visual Studio. I'm guessing it's because the people they get to work on AI stuff are AI People who probably only write in Python
Compilations break all the time and those symbols either become useless or it’s just quicker to use grep.
Earlier quoted context omitted.
That was great, thanks for the write-up. It’s rare to get a peek into Palantir’s ontology-forward approach. I’ve certainly been curious. > But it would make no sense to have an LLM regurgitate an existing form document token-by-token rather than call a piece of 1994 software like Hotdocs to populate some placeholders. This is a real “oof”, isn’t it. Very difficult to understand what they were going for here. Perhaps…
Really glad you liked it! Yes, I suspect it was just for show since a plain document popping onto the screen would just be jarring. Edit: looks like you’re in London, too. Hit me up and let’s connect. My details are in the bio!
In my research grep is fine if you don’t care about tokens and you have less than 100k files. The direct corpus interaction paper [1] shows a breakdown past this level. In my personal experience you get a bit better relevance than a BM25 search engine with grep plus an agent. But it requires you to eat tokens. If you think grep is great, it’s because you’ve been social engineered to organize your content to be findab…