21. Highly recommended read. This is the type of interpretability work that we need more of. "We can n... Highly recommended read. This is the type of interpretability work that we need more of. "We can now understand most neurons in models up to trillions of parameters, and think the 10/16 01:51 ♡
22. This is super cool. Texting a business should be as easy as texting a friend. At least that should b... This is super cool. Texting a business should be as easy as texting a friend. At least that should be the standard. @usebland turns any business website into a branded text line wi 10/16 01:18 ♡
23. Build for agents, folks! Agents will do more and more work inside business software, so every app n... Build for agents, folks! Agents will do more and more work inside business software, so every app needs to work through APIs and permissions. @ERPdotAI builds that in from the star 10/16 01:03 ♡
24. Agents need a better interface. In my own agent orchestrator, I often render more actionable, valua... Agents need a better interface. In my own agent orchestrator, I often render more actionable, valuable outputs as small interfaces. @openuidev makes this easy for any AI app. It is 10/16 00:56 ♡
25. Recommended, must-read paper on building recursive, self-improving agent harnesses for open-world ta... Recommended, must-read paper on building recursive, self-improving agent harnesses for open-world tasks. DAIR.AI @dair_ai Learn to build custom harnesses, folks! Here is a highly r 10/15 23:32 ♡
26. Must-read paper from Sakana AI on orchestrating coding agents for scientific research. (bookmark it... Must-read paper from Sakana AI on orchestrating coding agents for scientific research. (bookmark it) This is an important read with lots of useful insights if you are building mult 10/15 22:06 ♡
27. Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's... Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search 10/15 05:52 ♡
28. New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL... New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Termi 10/15 04:29 ♡
29. Ninety minutes of daily use per user is wild for Status. My instinct was that cost just comes with... Ninety minutes of daily use per user is wild for Status. My instinct was that cost just comes with the territory at that scale, but Inworld cut it by roughly 95% for them. fai nur 10/15 02:37 ♡
30. There is a huge opportunity for specialized personal agents. Here is a great example: @OdessiaTrav... There is a huge opportunity for specialized personal agents. Here is a great example: @OdessiaTravel just launched one for travel and experiences. You text it what you want, and it 10/15 02:11 ♡
