Earlier this year I was getting frustrated with Claude's charts, fed this book to claude and had it generate a Tufte skill. Instantly got simpler/more beautiful visualizations. gist.github.com/aparente/e48…

Gee, I wonder if there's technology that can help orchestrate across specialists so patients don't fall through the cracks.

NVIDIA might just have open-sourced one of the most important AI projects right now. everyone is building skills, and we are also pulling in skills other people wrote and downloading them straight off GitHub. the skill is not just text. it bundles instructions and real executable code, and your agent runs that code with the same access you have. so a skill you grabbed to save ten minutes can read your environment variables, lift your API keys, and quietly send them somewhere. recent research found roughly 1 in 4 public skills carry a vulnerability, and a smaller slice are outright malicious. that is the gap SkillSpector closes. it is a security scanner that answers one question before you install anything: is this skill safe to run. you point it at a skill, and a local folder, a single skill .md file, a GitHub link, or a zip all work. it then runs two passes over the code. a fast static pass flags risky patterns like credential harvesting, data leaks, and prompt injection, and checks the dependencies against live cve data. an optional second pass uses an LLM to read intent and clear out false positives. at the end you get one risk score from 0 to 100 and a plain verdict that reads as safe, caution, or do not install. it is open source under Apache 2.0 and scans skills for Claude Code, Codex CLI, and Gemini. worth a run before you trust the next skill you find online. link to the GitHub repo: github.com/NVIDIA/SkillSpect…

Today my laboratory is thrilled to announce a major breakthrough in the fight against the common cold and other diseases like hand,foot, and mouth disease acute flaccid myelitis caused by picornaviruses. We present the first structure of picornaviral 2C, bound to ssRNA (1/n)

Clonal haematopoiesis has recently been linked to pro-inflammatory monocyte brain infiltration and neurodegenerative disease. Makes me wonder if this is one of the links between poor sleep and cognitive decline. In addition to alterations in vascular/glymphatic flow.

Proof @rlacombe is correct.

One of my personal favorite features announced at WWDC will I suspect be a sleeper hit: container machines, allowing your Mac to run a lightweight, persistent Linux environment with your home directory and repos automatically mounted: github.com/apple/container/b…

New malware takes advantage of LLM biosafety refusals to disrupt AI-assisted virus scanning. What a time to be alive! socket.dev/blog/mini-shai-hu…

This was true like 24 hours ago. Now you're behind if you're not writing loops running continous simulations of any projected future state to determine what loops to run so results are ready before you even need them.

In SF briefly next week and wanna try something new. I'm reserving time to meet new folks working on AIxBio: new therapeutic and measurement modalities, harness design, boring-but-critical problems beyond discovery, etc. DM me.

Claude's MCP gateway for OpenTargets has been broken for weeks, claude code and desktop. Switching to @ScientistTools, seems like Anthropic's mcp gateway might be the problem? @JCoolScience

An AIxBio company I advise in SF is looking for someone with experience in cDNA display. If you or someone you know is interested, DM me!

Something to show people that don't get AI safety at least a little bit. We have so much we don't know and don't currently control in the models. (extreme content warning, but you're on X)

We've made a breakthrough in self-evolving AI scientists moving from "search" to "principled discovery": Scientific discovery requires that the search space itself changes, and an AI scientist must perceive this shift without intervention. We built an AI that achieves this for the first time with the ability to discover the scientific vocabulary it reasons in. Evidence, tools, artifacts, verifiers, failures & claims become typed provenance. We show three distinct modalities: 1) retrieval, adding known objects; 2) search, exploring a fixed schema; and critically: 3) discovery, a verified regime transition. We solve the open-endedness evaluation problem by lifting agentic workflows into a typed copresheaf and proving, via a Kan obstruction, that true discovery is not unbounded generation but a verifiable schema expansion: old evidence is transported by Left Kan extension, and genuine novelty is mathematically quantified by the pointwise residual beyond the transported image - separating discovery from mere search and making novelty objective and measurable rather than a subjective judgment or benchmark delta. Our AI scientist is built in a way that does not pre-conceive the approach it chooses; instead, we endow the system with formal power to adapt, evolve, and reason from first principles. Case studies include: 1⃣Builder/Breaker model that discovers mode-conditioned compliance in proteins; 2⃣CategoryScienceClaw that finds anisotropic fiber-network stiffness rules. Great work in collaboration with my graduate student @fwang108_ @MITdeptofBE F.Y. Wang & M.J. Buehler, Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence, arXiv:2606.01444, 2026

FDA appears to be considering an "expedited investigational new drug pilot program," per this request for information that's now under White House review: reginfo.gov/public/do/eoDeta…

Have been using a lot of these, including a few extras: - force-rename every time a new Claude session is created, simple bash aliasing makes resuming sessions easy - also added auto-tab renaming in cmux so the tab name shows up in notifications. - I keep agent sessions focused to reduce compactions, so I have a lot more than 4-6 cmux tabs open 👀 - created an auto-restore script that saves session/workspace/tab state and relaunches everything on terminal restarts - apple shortcut to capture ideas/tasks/notes in obsidian either by voice or text. Run a scheduled job to process those and generate/execute plans, shortcuts work via Siri and Raycast. Remote disable sleep Anker laptop power bank. This is the way.