elvis

Go-to-market is quickly becoming an engineering problem. Good outreach depends on clean lead data and on giving your AI agent the right con...

Pay close attention to harnesses, part 2. Last week I shared a paper where a model more than doubled its score after training inside the ha...

Pay close attention to agentic search. LLM agents get much better at specialized tasks when you give them structured, expert knowledge. Xe...

This is my new favorite way to keep up with AI papers. I turn my curated papers into a 2-minute spoken technical briefing with @FishAudio D...

Own your intelligence stack, folks! Open models, open data, and open harnesses are where a lot of the real agent building is happening righ...

AI video creation is a really huge market. It's really taking off in areas like marketing, education, and customer support. This team @cl...

This is a good example of what a company brain unlocks and how it compounds. You want it so that when someone on your team figures out a gr...

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes...

1M-token, multimodal decision models are here! But there is more to this one. You can classify, extract, and summarize with 1M tokens of ...

Richer context is what makes personal agents personal. Today, they see your email, calendar, and accounts, and miss everything happening i...

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is ...

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...

Pay attention to decision models. From my recent tests, decision models can be extremely transformative for businesses. Many calls in an a...

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 s...

Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent...

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 e...

Great paper from Meta Superintelligence Labs on compounding inference for long-horizon agents. One clear approach that's working with large...

Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B go...

Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through...

Bullish on this trend of making post-training more accessible. A new post-training era is upon us. If you work on agentic RL, long-contex...