johnschulman2 Profile Banner
John Schulman Profile
John Schulman

@johnschulman2

Followers
69K
Following
3K
Media
6
Statuses
140

Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music

Joined May 2021
Don't wanna be here? Send us removal request.
@johnschulman2
John Schulman
2 days
Happy to share a new paper! Designing model behavior is hard -- desirable values often pull in opposite directions. Jifan's approach systematically generates scenarios where values conflict, helping us see where specs are missing coverage and how different models balance
@jifan_zhang
Jifan Zhang
4 days
New research paper with Anthropic and Thinking Machines AI companies use model specifications to define desirable behaviors during training. Are model specs clearly expressing what we want models to do? And do different frontier models have different personalities? We generated
13
46
610
@ben_golub
Ben Golub
5 days
I am super excited to share a new AI tool, Refine. Refine thoroughly studies research papers like a referee and finds issues with correctness, clarity, and consistency. In my own papers, it regularly catches problems that my coauthors and I missed. 1/
36
198
1K
@johnschulman2
John Schulman
5 days
We're happy to support the Human Centered LLMs course, on topics close to our hearts. We'd like to support more classes with free credits for students to use on assignments and projects. If you're an instructor interested in using Tinker in your course, please reach out to
@Diyi_Yang
Diyi Yang
6 days
Thanks @thinkymachines for supporting Tinker access for our CS329x students on Homework 2 😉
15
52
613
@johnschulman2
John Schulman
6 days
Lead author @egler92630
0
1
23
@johnschulman2
John Schulman
7 days
Fine-tuning APIs are becoming more powerful and widespread, but they're harder to safeguard against misuse than fixed-weight sampling APIs. Excited to share a new paper: Detecting Adversarial Fine-tuning with Auditing Agents ( https://t.co/NqMeGSCQIF). Auditing agents search
Tweet card summary image
arxiv.org
Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM...
10
48
462
@willccbb
will brown
8 days
tinker 🤝 environments hub :)
23
27
369
@karpathy
Andrej Karpathy
15 days
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,
663
3K
24K
@johnschulman2
John Schulman
22 days
Great to see an open source backend in the works for the Tinker API. If Tinker is going to power open science and open software, it shouldn’t depend on a single proprietary implementation.
@pcmoritz
Philipp Moritz
22 days
The Tinker API recently released by Thinking Machines will have a big impact on how people think about post-training and inference systems. To allow more people to experiment with Tinker like systems and run it on their own hardware, we started SkyRL tx 🧸, an open source project
1
24
380
@johnschulman2
John Schulman
23 days
Even if I've tested a result extensively, it's hard to know how well it'll generalize to different experimental setups and software stacks
2
0
57
@johnschulman2
John Schulman
23 days
Really happy to see people reproducing the result that LoRA rank=1 closely matches full fine-tuning on many RL fine-tuning problems. Here are a couple nice ones: https://t.co/x7hcgNL3Bd https://t.co/5JyKuKd9wS
@zzlccc
Zichen Liu
26 days
much more convinced after getting my own results: LoRA with rank=1 learns (and generalizes) as well as full-tuning while saving 43% vRAM usage! allows me to RL bigger models with limited resources😆 script: https://t.co/p6IIiBQA6c
13
86
955
@johnschulman2
John Schulman
27 days
Tinker provides an abstraction layer that is the right one for post-training R&D -- it's the infrastructure I've always wanted. I'm excited to see what people build with it. "Civilization advances by extending the number of important operations which we can perform without
@thinkymachines
Thinking Machines
27 days
Introducing Tinker: a flexible API for fine-tuning language models. Write training loops in Python on your laptop; we'll run them on distributed GPUs. Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!
49
115
1K
@johnschulman2
John Schulman
1 month
Big fan of Jeremy’s work on optimization—great to see his first Thinking Machines post!
@thinkymachines
Thinking Machines
1 month
Efficient training of neural networks is difficult. Our second Connectionism post introduces Modular Manifolds, a theoretical step toward more stable and performant training by co-designing neural net optimizers with manifold constraints on weight matrices.
12
29
527
@sainingxie
Saining Xie
2 months
good question... thinking back to pre-LLM interviews I experienced (before 2019)… they were all in-person on-site, no chance of ''llm cheating,'' very different across places, and somehow way more memorable. > old deepmind had brutal ''quizzes'' -- 2-hour marathons with 100+
@giffmana
Lucas Beyer (bl16)
2 months
At which of these places did you have the coolest interview in your career? I know it's an ill-posed poll, but what am i gonna do with only 4 options?! I tried grouping them by interview similarity to the best of my knowledge. Comment if "other". Might make a second round.
21
123
2K
@johnschulman2
John Schulman
3 months
I'm more annoyed at whoever named us homo sapiens sapiens
@andrew_n_carr
Andrew Carr 🤸
3 months
Thinking vs think vs thinking-think
34
7
469
@miramurati
Mira Murati
3 months
Thinking Machines Lab exists to empower humanity through advancing collaborative general intelligence. We're building multimodal AI that works with how you naturally interact with the world - through conversation, through sight, through the messy way we collaborate. We're
649
700
8K
@johnschulman2
John Schulman
5 months
For people who don't like Claude's behavior here (and I think it's totally valid to disagree with it), I encourage you to describe your own recommended policy for agentic models should do when users ask them to help commit heinous crimes. Your options are (1) actively try to
123
41
716
@johnschulman2
John Schulman
6 months
A research project related to sycophancy: define explicit features like "does the response agree with the user" as in https://t.co/Ev5Q2PrpjK, and then construct a preference function that subtracts out their effect, as in https://t.co/kEaBgqar9V. I.e., remove some bad causal
8
21
278
@johnschulman2
John Schulman
6 months
Whether to collect preferences ("do you prefer response A or B?") from the same person who wrote the prompt, or a different person, is important and understudied. Highlighted this question in a recent talk https://t.co/7fcGmvG1Kd. Sycophancy probably results when you have the
@BlackHC
Andreas Kirsch 🇺🇦
6 months
This is serious, and we should make sure to prevent sycophantism as much as possible... Related: have we tried using other humans' feedback for RLHF instead of the original prompter's? This might somewhat help with debiasing 🤔
13
35
379
@johnschulman2
John Schulman
8 months
Excited to build a new AI research lab with some of my favorite former colleagues and some great new ones. Looking forward to sharing more in the coming weeks.
@thinkymachines
Thinking Machines
8 months
Today, we are excited to announce Thinking Machines Lab ( https://t.co/gD5QlPMfWw), an artificial intelligence research and product company. We are scientists, engineers, and builders behind some of the most widely used AI products and libraries, including ChatGPT,
41
48
1K
@johnschulman2
John Schulman
9 months
Actually 2 days ago, not last week :)
1
1
35