Omar Khattab

@lateinteraction

asst professor @MIT CSAIL @nlp_mit. ColBERT.ai, DSPy.ai (@DSPyOSS), GEPA, RLMs, Pedagogical RL

Cambridge, MA

omarkhattab.com

Replies Reposts Media

Omar Khattab
@lateinteraction
Sep 26
the only correct perspective on stochastic parrots
Omar Khattab
@lateinteraction
Feb 21
I don’t get all the hate that the phrase “stochastic parrots” gets. The main thing you should learn from all this is just how powerful very very very large parrots would be.
10
Omar Khattab
@lateinteraction
Sep 26
Jeffrey Ladish
@JeffLadish
Sep 25
Replying to @JeffLadish
The agents needed a browser to run their attack code. So they used a public screenshot website, which loads a virtual browser and takes a screenshot. But that virtual browser runs code, and so the agents could use it to send malicious payloads to Hugging Face’s servers.
23
Omar Khattab
@lateinteraction
Sep 25
whoa! so clean. the more the world changes, the more dspy stays the same at the interface level and very very different below the surface
Isaac Miller 🧩
@isaacbmiller1
Sep 25
DSPy 3.4.0 was just released! This release includes native support for Jev and System one models inside of DSPy! Use it with compatible signatures. This release also includes a brand new optimizer, ReAnchor, specifically for calibrating outputs with confidence.
10
Omar Khattab
@lateinteraction
Sep 23
i have something to release/share tomorrow that i think is very badly needed and has been so for a few years - it’s a tiny start and won’t be complete but i hope people will find it as useful and fun as i have enjoyed producing it
28
Omar Khattab
@lateinteraction
Sep 19
my quick and dirty analogy for the model's flavor of jaggedness in 2026 is kind of like... if you ask for a taxi ride but someone hands you a catapult that is highly pre-aimed on a very small number of destinations in advance initially, you're super impressed by the speed and
Omar Khattab
@lateinteraction
Sep 19
i don't see enough of this, so here again: we're all wondering what the future of work looks like with AI progress, but I'm in constant agony trying to extract OK work from frontier models at "Ultra" settings with levels of detailed context and elaborate feedback that i’ve
14