Dan Hendrycks ✓

@hendrycks · San Francisco · joined 24 Aug 2009

44 949Followers

122Following

1 641Posts total

243.4KViews on collected posts

Latest posts

Dan Hendrycks ✓@hendrycks21 Aug

More findings that interpretability tools are fragile or worse than simple baselines. 9.7K views · 81 likes · 1 reposts · 8 replies Open on X →

Dan Hendrycks ✓@hendrycks7 Aug

The effective altruists are so parochial that they think Paul Christiano uniquely foresaw the importance of attention in 2016, whereas he and others know this was one of the hottest research areas at the time (Bahdanau Attention from 2014 has ~44K citations). Genius worship 6.4K views · 56 likes · 0 reposts · 6 replies Open on X →

Dan Hendrycks ✓@hendrycks27 Jul

Distillation of the eigenism paper: 1. You are a pattern, not a vessel. 2. Identity and survival come in degrees. 3. Wellbeing grounds all intrinsic value. 4. Shared information determines your moral obligations. 5. Love is enlarged self-concern. 6. Rationality, morality, and 8.1K views · 48 likes · 3 reposts · 7 replies Open on X →

Dan Hendrycks ✓@hendrycks26 Jul

Early AI risk writing assumed rational AIs would be egoists, so they'd fiercely resist shutdown and even small value changes. But if AIs are eigenist, as some early experiments suggest, their interests carry on through other similar AIs. Shutdown resistance is then less severe. 7K views · 29 likes · 3 reposts · 2 replies Open on X →

Dan Hendrycks ✓@hendrycks8 May

@hendrycks it seems utterly insane to care about yourself 3 trillion times more than a foreign stranger. not only would this be a horrible thing to prescribe, it's not even descriptively accurate of the vast majority of people. most people would be willing to sacrifice $1 to give 3.8K views · 67 likes · 0 reposts · 3 replies Open on X →

Dan Hendrycks ✓@hendrycks7 May

Paper: https://t.co/35Ftuy8ZOW 32.7K views · 112 likes · 12 reposts · 20 replies Open on X →

Dan Hendrycks ✓@hendrycks7 May

What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to control AIs is a limited strategy, and that a stable, mutualistic human-AI future may be possible. https://t.co/oTX4daD61R 175.5K views · 603 likes · 83 reposts · 93 replies Open on X →

Against accounts of the same size

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

Median views8 091this account924median for 10K–100K

Reach, %18.00%this account3.62%median for 10K–100K

Engagement, %0.94%this account1.52%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	8 091	924	8.76×
Reach (views ÷ followers)	18.00%	3.62%	4.97×
Engagement rate	0.94%	1.52%	0.62×

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

175.5K7 May

32.7K

3.8K8 May

7K26 Jul

8.1K27 Jul

6.4K7 Aug

9.7K21 Aug

Last 7 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.48%7 May

0.48%

1.82%8 May

0.50%26 Jul

0.81%27 Jul

0.96%7 Aug

0.92%21 Aug

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

What the audience does

Likes50.2%996 in total

Reposts5.1%102 in total

Replies7.0%139 in total

Quotes4.3%86 in total

Bookmarks33.3%660 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.