Viewing profile — anishathalye

I recently gave a guest lecture on AI Agent Security in MIT's 6.566 class (a survey course on computer systems security). We covered: - Foundations of LLMs, from next-token predict…

I was working on AI in 2018 too :) At that time, I was quite interested in adversarial examples and ML security.

MIT already has an excellent class on Ethics for Engineers: https://e4e.mit.edu/

We returned to MIT last month to teach a revised version of Missing Semester, six years after the original debut (which has been extensively discussed on HN, in https://news.ycombi…

We (@anishathalye, @jjgo, @jonhoo) returned to MIT during IAP (January term) 2026 to teach a new iteration of Missing Semester, a class covering topics that are missing from the st…

Good point, I see how the example can be confusing. Updated the example to have `reverse=True` and a comment, hopefully that clarifies things.

For sure! I share your feelings about good science and honesty in academia :)

Yeah, that was just a design choice that I made: I wanted a library that worked with `Iterator`s, felt more lightweight to me / fit my immediate needs better. I'm personally not a …

I think semantic data processing in this style has a nonempty set of use cases (e.g., I find the fuzzy sorting of arXiv papers to be useful, I find the examples in the docs represe…

That was a small self-contained example that fit above the fold in the README (and fwiw even last year’s models like GPT-4o give the right output there). That `sort` is based on pa…

Hi HN! I've been thinking a lot about semantic data processing recently. A lot of the attention in AI has been on agents and chatbots (e.g., Claude Code or Claude Desktop), and I t…

Looks like the 2023 lectures weren't uploaded to YouTube, but the lectures from earlier iterations of the class, including 2022, are available publicly. For example, see the YouTub…

Implementing an ACME client is part of the final lab assignment for MIT’s security class: https://css.csail.mit.edu/6.858/2023/labs/lab5.html

I see someone posted this before I was able to do it :) Hi HN! For the last six years, I've been working on techniques to build high-assurance systems using formal verification, wi…