
🍄
110 posts



Be careful using Lambdas as isolated agent environments. One thing I learned the hard way: /tmp does not auto-clean between invocations on a warm Lambda. If one agent run leaves files behind, the next run on the same instance can see them. That can mean: > data leaking between sessions > weird nondeterministic bugs > disk filling up over time Always treat /tmp as potentially dirty state.









SECURITY ADVISORY — TanStack npm packages A supply-chain compromise affecting 42 @tanstack/* packages (84 versions total) was published to npm earlier today at approximately 19:20 and 19:26 UTC. Two malicious versions per package. Status: ACTIVE — packages are deprecated, npm security engaged, publish path being shut down. Severity: HIGH — payload exfiltrates AWS, GCP, Kubernetes, and Vault credentials, GitHub tokens, .npmrc contents, and SSH keys. If you installed any @tanstack/* package between 19:20 and 19:30 UTC today, treat the host as potentially compromised: • Rotate cloud, GitHub, and SSH credentials immediately • Audit cloud audit logs for the last several hours • Pin to a prior known-good version and reinstall from a clean lockfile Detection — the malicious manifest contains: "optionalDependencies": { "@tanstack/setup": "github:tanstack/router#79ac49ee..." } Any version with this entry is compromised. The payload is delivered via a git-resolved optionalDependency whose prepare script runs router_init.js (~2.3 MB, smuggled into each tarball at the package root). Unpublish is blocked by npm policy for most affected packages due to existing third-party dependents. All 84 versions are being deprecated with a SECURITY warning, and npm security has been engaged to pull tarballs at the registry level. Full technical breakdown, complete package and version list, and rolling status updates: github.com/TanStack/route… Credit to the security researcher for responsible disclosure.

YEAH

I really can't live without @aarondfrancis' Solo anymore.


starting to think now that every agent should have just 2 tools. search and execute. we _want_ agents to have access to 100s, if not 1000s of capabilities, that can contextually change during their lifetimes, even per message. saying stiff like "just use bash" doesn't encompass 3rd party apis, and you don't want to keep switching up the base prompt all the time. you gotta generalise that. I also guess search has to be semantic, so probably something with a vector db type thing. does it run on every message? probably...





For 100% agent-written frontends, I keep coming back to this: Maybe we don't start with a frontend framework Maybe we start with an index.html, browser primitives, Web Components for reusable UI and a strict convention for how agents route, render, mutate state and handle data








