_kidlike

he did not invent anything AFAIK. but it's the first cohesive work around this (that I've found).

I agree on the first part. the last part is simply wrong. adding engineering principles around AI have measurable outcomes (at least for software development). look at Agent Control Theory from Mark Pollack.

sounds very similar to jte.gg for Java

x402.org

lmao

for the same reason we used ElasticSearch for vector search, because it's just one part of a query. Everything else we already had (filters etc), just stay and can be combined with vector search.

this looks awesome! A very naive question, because I never bothered to learn how it works, but can I embed this in markdown files with ```reladraw, as I can do with ```mermaid? Mermaid gets rendered inside markdown files, in both IntelliJ and Github. I assume both added support for it at some point. But I don't know the mechanics of how this works. I wouldn't be able to use this until then, unfortunately.

that exactly how the Greek word sounds :)

ιστορία, if you wanna copy paste.

and yes, the English word comes from the Greek word!

can we choose read-after-write consistency at query time, if needed?

Do you know if Opus 5.1 is coming and will have improvements in writing style too?

:exploding-head:

I didn't say this is not supported. But it's not as good as streaming from Spotify directly to the amp, and the media decoding happens locally.

Adding the Bluetooth layer adds more layers of encoding/decoding, and generally speaking it has narrower bandwidth.

Also, I know it's a bit niche, but Deezer does not have an equivalent of "Spotify Connect" protocol, which means that Network Integrated Amplifiers (like Onkyo A-50), CANNOT implement a player with good UX. Spotify is now king since they introduced lossless quality which is enabled by default in such amplifiers. The benefit is that there is no local streaming (e.g. Bluetooth) and no latency. The data come from Spotify directly to the amplifier and then your speakers.

So, Deezer that had a audiophile target audience, has effectively lost the game.

JetBrains is a good option - works with any model/agent. Also they have very good semantic search for the codebase, which is exposed via MCP to the agents.