anishathalye.bsky.social @anishathalye.bsky.social · 21/09/2026I wrote software to help me run the optimal running route for Angel Island, covering the island's 19.4 miles of unique road/trail in the shortest possible distance of 23.8 miles. 100
anishathalye.bsky.social @anishathalye.bsky.social · 18/05/2026Demo gods were on my side for this guest lecture on AI Agent Security at @csail.mit.edu: I was able to show a prompt injection attack against @anthropic.com's Opus 4.6 model. Agent security is still an unsolved problem! 110
anishathalye.bsky.social @anishathalye.bsky.social · 19/02/2026Had a blast returning to @csail.mit.edu for IAP 2026 and teaching Missing Semester with @jonhoo.eu and @josejg.bsky.social! Hope the community enjoys the content, and would love to hear any feedback. 060
anishathalye.bsky.social @anishathalye.bsky.social · 11/09/2025I replaced Python's built-in functions with semantic operators. (1/) 120
anishathalye.bsky.social @anishathalye.bsky.social · 10/09/2025Current first-world problem: avoiding em-dashes so my writing doesn't look "AI-generated." Been using 'em since 2014, and yep—my blog posts are in Common Crawl. I guess I did this to myself? 010
anishathalye.bsky.social @anishathalye.bsky.social · 30/08/2025Always fun to see when a grad school side project grows to the point where it's powering real systems! Nice blog post from the S2 developers on how they do linearizability testing with deterministic simulation (using, among other tools, Porcupine): s2.dev/blog/lineari...s2.devLinearizability testing S2 with deterministic simulationHow we validate strong consistency 020
anishathalye.bsky.social @anishathalye.bsky.social · 23/08/2025Coding agents follow "it's always your fault" a bit too well. When they hit a compiler bug, they'll rearrange methods, tweak syntax, and go in circles rather than consider the tooling might be wrong. Had to manually identify and minimize this mypy bug after Claude Code couldn't. 120
anishathalye.bsky.social @anishathalye.bsky.social · 05/08/2025Missing Semester has grown past 100K subscribers on YouTube. Appreciate all the engagement and support! We plan to teach another iteration of the course in January 2026, revising the curriculum and covering new topics like AI IDEs and vibe coding. 2124
anishathalye.bsky.social @anishathalye.bsky.social · 21/06/2025My favorite way to measure progress in AI: finding papers obsoleted by ChatGPT prompts 100
anishathalye.bsky.social @anishathalye.bsky.social · 17/06/2025Ever get blinded when writing code late at night and you alt-tab from your dark-mode terminal to your browser? Made this little macOS utility to solve this little problem, just updated for the latest macOS. No thanks to AI for hallucinating BrightnessKit.framework. 100
anishathalye.bsky.social @anishathalye.bsky.social · 24/04/2025We reproduced (and fixed!) Cursor’s rogue customer support AI. (1/5) 100
anishathalye.bsky.social @anishathalye.bsky.social · 16/04/2025Coincidence, or genius growth hack? Cursor self-propagating through developer set-up instructions. 100
anishathalye.bsky.social @anishathalye.bsky.social · 08/04/2025Is AI any good at evaluating AI? Is it turtles all the way down? We benchmarked evaluation models like LLM-as-a-judge, HHEM, Prometheus across 6 RAG applications. 1/2 110
anishathalye.bsky.social @anishathalye.bsky.social · 17/02/2025A substantial portion of traffic for some of my open-source projects comes from ChatGPT these days. Sometimes even a majority, beating traffic from Google. Time to prioritize LLM optimization over search engine optimization. (1/3) 110
