Demo 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!

Had 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.

Jon Gjengset@jonhoo.eu · 6mo ago

In January, @anishathalye.bsky.social, @josejg.bsky.social, and I returned to @csail.mit.edu to teach Missing Semester, a class on topics we miss from most CS programs—tools and techniques that everyone should know, like Bash, Git, CI, and AI tools. Today, we’re releasing the course for free online!

I replaced Python's built-in functions with semantic operators. (1/)

Current 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?

Always 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...

Linearizability testing S2 with deterministic simulation

How we validate strong consistency

s2.dev

Coding 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.

Missing 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.

My favorite way to measure progress in AI: finding papers obsoleted by ChatGPT prompts

Ever 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.

We reproduced (and fixed!) Cursor’s rogue customer support AI. (1/5)

Coincidence, or genius growth hack? Cursor self-propagating through developer set-up instructions.

Is 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

A 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)