Joe Fox

Apparently March is agent finance stack announcement month

A lot of AI content can be categorized as shiny coins or dull $100 bills often taking the same amount of time to consume.

Agentic organizations & companies as well as governance & orchestration approaches have me thinking more about org culture. Lots of individual approaches on agent persona/values, surprised there isn't a pip repo to distill "culture" from one group of agents to another. Could easily see the agentic persona marketplace moving into these areas.

Interesting on persona dropout technique: humanlm.stanford.edu/blog_persona.h…

Should skill md files have "nutritional facts" or outline of risks?

Making Wolfram tech available as a Foundation Tool for LLM foundation models... writings.stephenwolfram.com/2026/02/making…

Have you seen any physical /stop buttons for OpenClaw yet?

What websites do OpenClaw agents visit for vacation?

Cool approach to deal with fragmented PII snippets across context

The multi vector embeddings are created using our SOTA retrieval model mxbai-wholembed. It supports text, audio, video on over 300 languages. A key innovation is the dynamic vector allocation, which lets the model dynamically decide the amounts of vectors it needs to represent information. For example, a simple cat image may output a few vectors, whereas a complex slide deck may generate thousands of vectors. We wrote a custom inference engine to serve mxbai-wholembed with low latency.

@joshgans @RemindMe_OfThis in one week.

I have a new paper out today. Gen AI shows a pattern: it excels at some tasks but fails at seemingly similar ones. This "jagged" performance creates a fundamental problem for users trying to decide when to rely on AI. I explain why this happens and what it means. 👇🧵

@m_finzi @ShikaiQiu @yidingjiang @Pavel_Izmailov @zicokolter @andrewgwils @RemindMe_OfThis to read in 1 week.

1/🧵 We are very excited to release our new paper! From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence arxiv.org/abs/2601.03220 with amazing team @ShikaiQiu @yidingjiang @Pavel_Izmailov @zicokolter @andrewgwils

New paper! A compromised inference server can leak model weights by hiding them in normal-looking responses🥷 But LLM inference is nearly deterministic, so we can verify outputs with a trusted server & detect this (and inference bugs) This slows data exfiltration by >200x 🧵

I want to update our list of resources for founders raising capital What should we include?