🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The animations in this thread may be a year old, but they’re still as informative as ever. An accessible thread on how dspy.MIPROv2 and its earlier variants have been optimizing tens of thousands of (multi-step) LM programs and agents since Jan 2024.

What if LLMs could learn your habits and preferences well enough (across any context!) to anticipate your needs? In a new paper, we present the General User Model (GUM): a model of you built from just your everyday computer use. 🧵

You can build prettyyyy good user models from just pairwise preferences too!!

Turn yourself into a prompt with "SynthesizeMe" so any LLM can be personalized for you? 👀 Another best-in-class application of dspy.MIPROv2.

SynthesizeMe personalizes LLMs by inducing synthetic user personas from interaction reasoning, without relying on demographics or predefined categories 🫡 Try it yourself: try-synthesize.me

super cool work from the goat Michael Ryan on personalization for LM's. Personalization is a (maybe even 'the') core problem in how humans will interact with language models going forward. Michael is a (maybe even 'the') goat researcher + presenter. This is very cool work!

Super comprehensive paper from Yijia Shao and Humiska asking a fundamental question: what tasks do people *want* automated by AI? This is my favorite figure, tons to learn from this work!

Earlier we released SynthesizeMe #ACL2025NLP — a method for building a personalized persona prompt from your LLM interactions 🤖. Wanted to highlight this video from the thread that gives a lot of intuition for how SynthesizeMe (and related prompt opt algos) work! 👇

AI companions aren’t science fiction anymore 🤖💬❤️ Thousands are turning to AI chatbots for emotional connection – finding comfort, sharing secrets, and even falling in love. But as AI companionship grows, the line between real and artificial relationships blurs. 📰 “Can A.I.

Are AI scientists already better than human researchers? We recruited 43 PhD students to spend 3 months executing research ideas proposed by an LLM agent vs human experts. Main finding: LLM ideas result in worse projects than human ideas.