I am still very bullish on local LLMs. We have yet to see its biggest unlock. I am particularly curious to see what's possible with unlimit...

Good to see this going GA. Long-running agents can handle a complicated task and still miss a step you'd assume was easy. I'd like to see w...

You don't see releases like this every day. Liquid AI just released LFM3, a family of ~2B open-weight models for text, vision, audio, omni...

Love seeing these open-source efforts. @Hi3D_AI recently released their 3D model, Hi3D V1.0. Built on Sparc3D, it uses a reference image to...

RAG is so back! Another paper showing that plain RAG keeps winning the agent memory comparison. They show that many dedicated memory syste...

"We saw a glimpse of the future of swarm coding." Agent swarms will fundamentally change how we build software. @axiommathai used a swarm ...

Highly recommended read if you work with coding agents. My general rule of thumb is to get out of the agents' way as much as I can. My t...

Impressive work on decision models for agentic search. Drex Search looks like a big upgrade for agents working over large file collections....

Protect your data, folks! AI is speeding up how fast vulnerabilities get found and exploited. Last week's PHP2Shell attacks showed how fast...

Learn to build a custom harness, folks! There is so much alpha in understanding how to optimize the harness. This work shows the benefits ...

After Jev, this is the most exciting System One model. Cloudflare introduced it last week. It's great for extraction tasks and complement...

📝 A Primer to Cloudflare's Clairic System One Extraction Model Clairic is a model that extracts specific values from unstructured text and...

Unfortunately, CLI agents are no longer the ideal interface for working with agents. This has been the case for months now. It hurts to ...

New paper from Google DeepMind on training models to argue well about moral dilemmas. The trained model became more decisive and stopped ch...

Highly recommended read on looped and depth-grown models. There is a lot of interest in looped and depth-grown language models for reasonin...

Banger guide by Anthropic. While frontier models have improved at context management, subagents still help in some cases (e.g., paralleliz...

Can LLMs improve their own harness? Self-improving harnesses are a hot topic. And one interesting question is whether LLMs can generate an...

Thariq is one of the only reasons I still continued to explore and use Claude Code. He always shared great insights worth trying. He set the...

Recommended leaderboard to track voice AI. They just added five new languages to the Voice Arena TTS leaderboard. ElevenLabs models rank #...

Really digging this new arc of specialized RL models. Bullish on this effort to understand and unlock collective intelligence. Highly recom...