No spam, ever. We'll never share your email address and you can opt out at any time. Already a subscriber? Log in
NLP and interpretability researcher
Our new paper reformulates tokenisation as a linear program (LP), which we solve to get SOTA tokenisers 😁 As a bonus, this LP tells us how close to optimal any tokeniser is! Check it out 👇 w/ J. Tempus, @philipwitti.bsky.social, @craigschmidt.com, D. Komm Paper: arxiv.org/abs/…
Benchmarks can be superficial, but model explanations and evaluations are fundamentally intertwined. What if we used interpretability as principled, scientific evaluation? If it met scientific standards? arxiv.org/abs/2605.05508 coming to EvalEval at ACL as oral 🧵 1/6
Our new paper sets the stage for the biggest practical use case of model interpretability: stress testing and dataset development. All you need is interpretable linear features and simple geometry.
I wrote this a few months ago right after the first Anthropic/DoW conflict & Citrini & Block: “t But I think that single week is a good illustration of what the near future will feel like… as the stakes go up, it is likely things will feel even more unstable..” www.oneusefulth…
NLP reviews suck! But why is not clear– @aclrollingreview.bsky.social provides *a lot* of guidance for how to review, but in that, first principles get lost. So @adamlopez.bsky.social and I have written down some of our thoughts on first principles.
Anthropic just got ordered to suspend all access to Mythos & Fable & every customer lost access overnight. This is why we built AISLE to run even on open-source models, air-gapped. We match Mythos on zero-days, based out of Europe: aisle.com/blog/aisle-matches-anthropic-mythos…
We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples? 🧵NEW PAPER by @jenniferlumeng.bsky.social
if you are a PhD student in AI, remember it is in your interests to distract your advisor from how much money they could be making in industry. should be a daily priority.
ok the thing about erdos is he obviously loved collaborating with humans. he could have done a lot on his own, but math was how he chose to connect. I'm not sure he would have been very into chatbots?
my new literary award cannot be won by a commercial frontier LLM because I will require that 10% of each submission is smut
I tried to make the theory work out but the computer devil kept lying to me (ChatGPT generated incorrect proofs)
Center = Naomi Saphra. 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.
