seems like flock is a great honeypot to find bad cops

And what do you do when you find them? Unless there are adequate consequences (and no, a paid vacation or getting “fired” and moving to the next town over don’t count) the abuses aren’t going to stop.

And schools must be great honeypots to find mass shooters too, huh. It’s not a honeypot if it’s real data

public roads are a great honeypot for citizens everywhere

that one platform is using a flipped chroma logo - chroma has nothing to do with this racket (source : i’m chroma’s ceo)

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.

Anthropic is, I believe, fully pursuing the idea that you shouldn't use their model with anything but their own products. They don't care whether it generalizes.

I agree it's very frustrating to use with custom tools/harnesses that can speed up the process for domain specific purposes.

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.

https://github.com/tobi/qmd

Both is usually the right answer, since you can use LLMs to do query expansion and effectively increase the recall performance of your retrieval algo

it will only use tools it was trained on? what's the benfit of givig it all the tools.

then you are not agi pilled

> I'm still disappointed that ai can't use ctags,

What do you mean by this? Do you mean not automatically build the index?

it inspects a project, finds the ctags files, then goes on to use grep.

last weekend I vibe-coded a project called `openfs` that plugs into just-bash

https://github.com/jeffchuber/just-bash-openfs

it puts a bash interface in front of s3, filesystem (real and in-memory), postgres, and chroma.

still very much alpha - but curious what people think about it.

see an example app here: https://github.com/jeffchuber/openfs-incident-app

I did a slightly less ambitious prototype a few weeks ago where I created added lazy loading of GCS files into the just-bash file-systems, as well as lots of other on-demand files. Was a lot of fun.

yeah (optional) caching is interesting to think about - incl write_through and write_back

What problem were you trying to solve ? ( not that you need to solve one. I’m just curious )

try out chroma or better yet as opus to!

that was me swyx

Multiple people have coined the idea repeatedly, way before you. The oldest comment on HN I could find was in December 2022 by user spawarotti: https://news.ycombinator.com/item?id=33856172

Here is an even older comment chain about it from 2020: https://news.ycombinator.com/item?id=23895706

Apparently, comparing low-background steel to pre-LLM text is a rather obvious analogy.

As well as that people often do think alike.

If you have a thought, it's likely it's not new.

Oh wow, great find! That’s really early days.

i didnt claim to invent it.

i claimed swyx heard it through me - which he did

you did!!

i support this

Good article - the most use cases i see of pg_vector are typically “chat over their technical docs” - small corpus - doesn’t change often / can rebuild the index - no multi-tenancy avoids much of the issues with post-filtering

Chroma implements SPANN and SPFresh (to avoid the limitations of HNSW), pre-filtering, hybrid search, and has a 100% usage-based tier (many bills are around $1 per month).

Chroma is also apache 2.0 - fully open source.

congrats to factory on the amazing product and release!

chroma stores both

As does Azure's AI search.