Eugene Yan ✓

@eugeneyan · Seattle ⇄ SF · joined 25 Apr 2009

MTS @AnthropicAI. Prev: Principal Applied Scientist @Amazon, led ML @ Alibaba, Healthtech startup.

29 359Followers

619Following

4 798Posts total

209.1KViews on collected posts

Latest posts

Eugene Yan ✓@eugeneyan1 Sep

Fable 5.1 is a thoughtful collaborator, thinking hard about my requests, proactively patching my blindspots, and verifying the work's correct without being asked. And with cache reads now costing 75% less, to $0.25/M tokens, huge savings for long-running, agentic tasks! 6.5K views · 46 likes · 3 reposts · 15 replies Open on X →

Eugene Yan ✓@eugeneyan22 Jul

When evaling models, we anchor on the median task. But this is like how devs estimate the median task accurately but underestimate the mean which tends to be ~2x estimated (thus "double your estimates"). This applies to models too—we optimize for time/cost on median tasks. But h

5.6K views · 28 likes · 4 reposts · 6 replies Open on X →

Eugene Yan ✓@eugeneyan20 Jul

Fable is careful. None of the other models are careful. GPT-5.6 Sol, Opus, Kimi, Grok. You can compare them all day long on capabilities, and it doesn't matter, because in order to use a model for real production work, it must first and foremost be careful. That's the only 174K views · 1.7K likes · 81 reposts · 305 replies Open on X →

Eugene Yan ✓@eugeneyan1 Jul

I’m at @aiDotEngineer and hanging out around the music corner on the 2nd floor from 1415 - 1515! Come by to chat about https://t.co/pdd8bk66Jz, https://t.co/eJSa2MISCW, https://t.co/51rtuo4PDO, evals, agents, memory, how to work effectively with claude code, claude tag, etc! 4.5K views · 44 likes · 5 reposts · 1 replies Open on X →

Eugene Yan ✓@eugeneyan25 Jun

How do we eval if a model can find and exploit vulnerabilities? We discuss some benchmarks and the common pattern: • A sandboxed target within Docker containers • Inputs: code only (0-day), with patch (1-day scenario) • Tools such as bash, static analyzers, etc. • A grader to 13.7K views · 80 likes · 11 reposts · 18 replies Open on X →

Eugene Yan ✓@eugeneyan23 Jun

I've been loving the multiplayer form factor of Claude Tag. Now others can reply on the thread to provide context and direction to Claude! 4.8K views · 13 likes · 0 reposts · 6 replies Open on X →

Against accounts of the same size

3 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views6 490this account924median for 10K–100K

Reach, %22.11%this account3.62%median for 10K–100K

Engagement, %0.99%this account1.52%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	6 490	924	7.02×
Reach (views ÷ followers)	22.11%	3.62%	6.11×
Engagement rate	0.99%	1.52%	0.65×

Others in this range → Compare with another account → How these benchmarks are built →

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

4.8K23 Jun

13.7K25 Jun

4.5K1 Jul

174K20 Jul

5.6K22 Jul

6.5K1 Sep

Last 6 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.39%23 Jun

0.80%25 Jun

1.12%1 Jul

1.21%20 Jul

0.70%22 Jul

0.99%1 Sep

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

What the audience does

Likes67.6%1 902 in total

Reposts3.7%104 in total

Replies12.5%351 in total

Quotes1.4%38 in total

Bookmarks14.8%417 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.