I've spent months rethinking and rebuilding my programming languages course from scratch for the agentic coding era. I wrote myself a memo explaining what I'm doing. I figure others might be interested in the redesign, so here goes! Feedback welcome of course. docs.google.com/…
Shriram Krishnamurthi
Articles & links
5/ We also have some (preliminary!) evidence that "if it types it runs", LLMs can infer semantics even w/out meaningful variable names, etc. THERE. ARE. A. LOT. OF. CAVEATS! Mostly posting this to inspire better research. All details are on arXiv: arxiv.org/abs/2606.01522
The Data Science Institute at Brown invites applications for an 18-month postdoc position in civic science and AI-human interaction. The successful candidate will be hosted by ARIA (the NSF AI Research Institute on Interaction with AI Assistants, which I'm part of). See: apply…
Recent commentary
New research thread: 1/ Error messages have always been designed, sometimes painstakingly, for humans. But now we have new "readers" for errors: agentic AI. Should this affect what PLs generate? Can we measure this experimentally? We have some preliminary results: ↵
Reading Arvind Narayanan made me think: one of the great (and most undersung) achievements of the 20th century was rural electrification. If "AI is the new electricity", what is "rural AIification"? "Rural" here is obviously a metaphor, though it has some literal elements too.
What even are we doing here. I'm not even sure what the ask is. This company wants me to pay them to run an AI that is going to feed my soundbites to…who exactly? No need, my soundbites are available for free right here. (-:
The fact that Claude Code can do all kinds of agentic things but not *checks watch* check a watch will never not be funny.
In Shriram Krishnamurthi's orbit
Center = Shriram Krishnamurthi. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.