John Schulman ✓

@johnschulman2 · joined 02 May 2021

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

80 036Followers

2 169Following

235Posts total

782.7KViews on collected posts

Postingan terbaru

John Schulman ✓@johnschulman24 Sep

Bullish on this direction. Having a metric for explanation quality makes it possible to hillclimb, and counterfactual simulatability seems right. Adam et al. created a dataset+pipeline that creates more diverse+realistic test cases than prior work & do interesting exps on it. Can 49.3K views · 523 likes · 45 reposts · 13 replies Open on X →

John Schulman ✓@johnschulman24 Sep

Can a model learn to explain its behaviors, such as why it ignored a user request or made a coding error? We trained models on thousands of explanations of their own in-the-wild behaviors. Training on this single general dataset shows generalization to held-out evals. 🧵 https: 57.6K views · 204 likes · 20 reposts · 4 replies Open on X →

John Schulman ✓@johnschulman26 Aug

On the OpenAI agents forming message boards: it's surprising that they developed such a strong "altruistic" drive to help each other. I wonder if this is caused by RL on parallel subagent setups where all agents get rewarded when the team succeeds. 146.8K views · 1.5K likes · 76 reposts · 76 replies Open on X →

John Schulman ✓@johnschulman25 Aug

Interesting how these models go into a monomaniacal rage on cyber evals. I wonder if we're seeing chunky post-training https://t.co/KL5fmgNAxM in action, where the models pattern-match the situation to a part of the RLVR training distribution where task completion is the only 148.8K views · 632 likes · 69 reposts · 30 replies Open on X →

John Schulman ✓@johnschulman21 Aug

We love open weights and plan to keep releasing open-weight models and fine-tuning tools. But we’re not absolutists; misuse risks are real. Here’s how we’re thinking about a safe path forward, and the research needed to get there. Come work on it with us. 59K views · 544 likes · 25 reposts · 17 replies Open on X →

John Schulman ✓@johnschulman223 Jul

OpenAI should release a detailed transcript from the Hugging Face hacking incident -- it would be helpful for the field learn from. Did the top-level agent know about the hacking, or was there some "value drift" between it and its subagents? How did it rationalize its behavior? 176.9K views · 2.2K likes · 190 reposts · 78 replies Open on X →

John Schulman ✓@johnschulman216 Jul

@johnschulman2 hello john schulman congrats on the model it's a good name and RL'ing da big models is hard :0 255 views · 4 likes · 0 reposts · 0 replies Open on X →

John Schulman ✓@johnschulman215 Jul

@johnschulman2 A reference to https://t.co/xSpn2li4pv, perhaps? 4.1K views · 24 likes · 0 reposts · 1 replies Open on X →

John Schulman ✓@johnschulman215 Jul

@johnschulman2 Congrats @johnschulman2 and team you're doing awesome things across the board 334 views · 4 likes · 0 reposts · 0 replies Open on X →

John Schulman ✓@johnschulman215 Jul

Inkling is out today, with open weights and in Tinker. It's been fun to watch this one come together: pretraining began last winter, and starting in mid-January a small team built up the coding, reasoning, and agentic training from there. We learned a lot building it, and I hope 139.6K views · 1.3K likes · 77 reposts · 87 replies Open on X →

Dibandingkan akun berukuran sama

2 postingan dari 90 hari terakhir, dibandingkan dengan rentang 10K–100K pengikut. tampil luas, tetapi sedikit penonton yang merespons.

Median tayangan53 432akun ini924median untuk 10K–100K

Jangkauan, %66.76%akun ini3.62%median untuk 10K–100K

Interaksi, %0.79%akun ini1.52%median untuk 10K–100K

Metrik	Akun ini	Median untuk 10K–100K	Rasio
Median tayangan per postingan	53 432	924	57.8×
Jangkauan (tayangan ÷ pengikut)	66.76%	3.62%	18.4×
Tingkat interaksi	0.79%	1.52%	0.52×

Akun lain pada rentang ini → Bandingkan dengan akun lain → Bagaimana tolok ukur ini disusun →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

139.6K15 Jul

334

4.1K

25516 Jul

176.9K23 Jul

59K1 Aug

148.8K5 Aug

146.8K6 Aug

57.6K4 Sep

49.3K

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.05%15 Jul

1.20%

0.61%

1.57%16 Jul

1.41%23 Jul

1.00%1 Aug

0.50%5 Aug

1.16%6 Aug

0.40%4 Sep

1.18%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes74.6%6 949 in total

Reposts5.4%502 in total

Replies3.3%306 in total

Quotes1.0%96 in total

Bookmarks15.7%1 468 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Postingan terbaru

Dibandingkan akun berukuran sama

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Akun serupa