Keep on to blur preview images; turn off to show them clearly
Since Lean has emerged as the referenced language for autoformalization, worth remembering how internal bug snowballed into reward hacking for DS-Prover-v2.
I'm not sure the landscape is settled at all and maybe it should not be. Lots of other languages used in specialized domains (typically to write rule-based constraints), except bench/dataset/recipes for synth are non-existent.
Can someone explain why companies use human-like userpics for their AI assistants? It's just beyond my understanding. #ai #design #ui
Building: Crisp AI plugin https://t.co/FU7rtswKQ9 Ex @microsoft
If I think of an AI agent, I think of something that can autonomously operate Claude Code etc still just respond to what I tell them
🇪🇺https://t.co/NdorAWqJC3 @euacc 📸https://t.co/lAyoqmSBRX $118K/m 🏡https://t.co/1oqUgfD6CZ $36K/m 🛰https://t.co/ZHSvI2wjyW $43K/m 🌍https://t.co/UXK5AFqCaQ $15K/m 👙https://t.co/RyXpqGuFM3 $14K/m 💾https://t.co/M1hEUBAynC $6K/m
RT @dominiksumer: this one's a bit overdue - data which is incomplete (e.g. for the current day), will be visualized as dashed lines on the…
building @VemetricHQ & @snappify_io
RT @DSPyOSS: Maybe we should start a DSPy podcast to understand the ground that advanced DSPy users are breaking in practice. Oh wait @get…
Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.
It's so heartening to open this site every day and amplify the latest buzz around ColBERT, DSPy, GEPA, and most recently Recursive Language Models (RLMs) 😁 Surprisingly these four circles are fairly distinct.
Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.