41. Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) ... Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become tr 10/13 21:57 ♡
42. 1M-token, multimodal decision models are here! But there is more to this one. You can classify, e... 1M-token, multimodal decision models are here! But there is more to this one. You can classify, extract, and summarize with 1M tokens of text and image input. ScaleDown's Const 10/13 20:26 ♡
43. @ @CollovLabs More information here: https://t.co/VTBA2P1Y3l @CollovLabs More information here: neweyesai.com/store 💬 0 🔄 0 ❤️ 3 👀 1817 📊 1 ⚡ Powered by xgo.ing 10/13 09:33 ♡
44. Richer context is what makes personal agents personal. Today, they see your email, calendar, and a... Richer context is what makes personal agents personal. Today, they see your email, calendar, and accounts, and miss everything happening in front of you. NewEyes AI from @CollovLab 10/13 09:28 ♡
45. Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for sca... Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's w 10/13 06:20 ♡
46. Agents are quickly becoming your API and docs' main users. The @readme team says agents now make up... Agents are quickly becoming your API and docs' main users. The @readme team says agents now make up 72% of traffic to API docs. And when an agent gets stuck, it rarely goes loo 10/13 02:50 ♡
47. Pay attention to decision models. From my recent tests, decision models can be extremely transforma... Pay attention to decision models. From my recent tests, decision models can be extremely transformative for businesses. Many calls in an agent workflow are structured decisions, so 10/13 01:19 ♡
48. Your agent traces are your best eval data. The most important failures only show up in production, ... Your agent traces are your best eval data. The most important failures only show up in production, and they rarely make it into your test set. DigitalOcean's Signals flags sess 10/12 23:23 ♡
49. Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently... Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. Th 10/12 21:54 ♡
50. This will be a fun one. @MilksandMatcha runs DevX at Cerebras and @vivianmshen is a General Partner... This will be a fun one. @MilksandMatcha runs DevX at Cerebras and @vivianmshen is a General Partner at YC. Two people who work deep in AI every day are now talking about what life 10/12 02:02 ♡
