1. L Learn how to build evals, folks! It's one of the pillars of the intelligence stack. Agents are hu... Learn how to build evals, folks! It's one of the pillars of the intelligence stack. Agents are hungry for data and can get it in many ways, but you can't build anything use 10/19 08:23 ♡
2. Nice paper on scaling data environments from scratch. They built an engine that creates data-analys... Nice paper on scaling data environments from scratch. They built an engine that creates data-analysis environments from scratch. They apply RL, which adds 20.9 points on DABstep-Ha 10/19 05:45 ♡
3. // Latent Semantic Memory for LLMs // This paper presents some really interesting findings about ag... // Latent Semantic Memory for LLMs // This paper presents some really interesting findings about agent memory. They find that sixteen memory tokens beat full-context inference on F 10/19 01:59 ♡
4. Great application of small language models from Salesforce and colleagues. AI-scientist pipelines a... Great application of small language models from Salesforce and colleagues. AI-scientist pipelines are well known to struggle to propose novel and diverse research ideas. This team 10/18 06:04 ♡
5. Mind-blowing to see these Pareto improvements in performance and cost. More than anything, it's cr... Mind-blowing to see these Pareto improvements in performance and cost. More than anything, it's crazy how quickly these improvements are landing across providers. This matters 10/18 03:50 ♡
6. Recommended paper integrating decision models like Jev into harnesses. Recommended paper integrating decision models like Jev into harnesses. DAIR.AI @dair_ai Must-read paper integrating decision models like Jev into harnesses. They distilled an open 10/18 00:35 ♡
7. Banger paper from Tencent on recursive self-improvement for terminal agents. (bookmark it) This is... Banger paper from Tencent on recursive self-improvement for terminal agents. (bookmark it) This is a great read if you are tracking research on training terminal or coding agents w 10/18 00:00 ♡
8. Real talk. PRs suck in the age of coding agents. There must be a better way. I agree with this post,... Real talk. PRs suck in the age of coding agents. There must be a better way. I agree with this post, agents are so capable now. Let them do the heavy lifting. They can generate (on 10/17 10:02 ♡
9. Surprised that so few people are talking about this. Persistence has become a core capability of re... Surprised that so few people are talking about this. Persistence has become a core capability of recent models (Opus 5.5, GPT 6 Astra, Gemini 4 Argon,...). I was just reading throu 10/17 04:38 ♡
10. Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI, the brains that... Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI , the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from a 10/17 01:22 ♡
