Keller Jordan ✓

@kellerjordan0 · San Francisco · joined 23 Mar 2016

CIFAR-10 fanatic Pretraining @OpenAI OpCo LLC. Personal opinion poster

19 317Followers

459Following

1 681Posts total

534.5KViews on collected posts

Against accounts of the same size

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

Median views9 348this account1 456median for 10K–100K

Reach, %48.39%this account4.50%median for 10K–100K

Engagement, %0.82%this account1.88%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	9 348	1 456	6.42×
Reach (views ÷ followers)	48.39%	4.50%	10.8×
Engagement rate	0.82%	1.88%	0.44×

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

6K13 Apr

5.6K

7.3K

6.8K

4.3K

6.5K

4.4K

4.4K

2.7K

80.2K27 Jun

8.6K13 Aug

75.6K14 Aug

8.9K18 Aug

9.3K4 Sep

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.91%13 Apr

0.55%

0.54%

0.75%

0.72%

0.70%

0.73%

0.97%

1.09%

0.24%27 Jun

0.83%13 Aug

0.71%14 Aug

0.94%18 Aug

0.85%4 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.88%.

What the audience does

Likes65.1%2 716 in total

Reposts5.0%210 in total

Replies2.5%106 in total

Quotes0.7%31 in total

Bookmarks26.6%1 112 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.

Latest posts

Not entirely. Human beings dedicating their lives to speedrunning provides a service that capitalism desperately needs: Affirmation that the greatness of the Computer Maniac way of life transcends capitalistic incentives. 9.3K views · 74 likes · 1 reposts · 4 replies 04 Sep 2026 Human civilizations are well-regularized by our mortality & inability to copy ourselves. Machine civs will have these regularization controls turned off. => No one knows if a global machine civ would even be stable: It could be like training MoE without load balancing. 8.9K views · 74 likes · 3 reposts · 6 replies 18 Aug 2026 Expanding on this: A human brain throughout its lifespan uses ~50GJ of energy. How far can you get using AI technology with 50GJ? Basically nowhere: Just training Llama 3 8B (a tiny model) used 3,000GJ. In fact, the power of machine intelligence has never been about being a 75.6K views · 467 likes · 32 reposts · 28 replies 14 Aug 2026 Not going to give examples, but it’s interesting how you can see a population of divisive posts on here which aren’t quite false enough to get directly community noted, but are certainly false enough to get debunked by any chatbot that you paste them into. I wonder what will 8.6K views · 63 likes · 0 reposts · 8 replies 13 Aug 2026 Broke: We should be careful about AI because it might mistreat humanity during its glorious conquest of the galaxy Woke: We should be careful about AI because a global swarm of immortal perfect-clone agents might be vulnerable to catastrophic fungal infections 80.2K views · 177 likes · 5 reposts · 9 replies 27 Jun 2026 @kellerjordan0 Neat 🥳 In DDU, we argue that bc the mutual information of an ensemble is also great for uncertainty estimation, this requires the members to disagree in their predictions, which leads to variance, so some will have to perform better and some worse 🤗 https://t.co/X 2.7K views · 27 likes · 1 reposts · 1 replies 13 Apr 2023 14/ It also wouldn’t have been possible to efficiently train the ~350K networks needed for it, without the FFCV library from @aleks_madry‘s lab. Thanks to @bneyshabur and @esiamid for their advisements during the project. 4.4K views · 38 likes · 1 reposts · 4 replies 13 Apr 2023 11/ These findings were obtained from studying standard, well-tuned trainings on CIFAR-10 and ImageNet. As a caveat, for unstable trainings (e.g. too high learning rate) variance exceeds the hypothesis and is certainly not harmless. https://t.co/UVEuUcviaF 4.4K views · 30 likes · 1 reposts · 1 replies 13 Apr 2023 13/ Shoutouts: This project was largely inspired by @david_picard‘s empirical study “Torch.manual_seed(3407) is all you need”. https://t.co/RFQHcr4mmB 6.5K views · 44 likes · 0 reposts · 2 replies 13 Apr 2023 12/ When trained networks are evaluated on distribution-shifted test-sets, there is also significant excess variance. https://t.co/t1qBl0vlTY 4.3K views · 28 likes · 0 reposts · 2 replies 13 Apr 2023 10/ My conclusions: variance is both _harmless_ (does not imply almost any differences in model quality) and _inevitable_ (cannot be gotten rid of without sacrificing other beneficial properties of training). 6.8K views · 47 likes · 2 reposts · 2 replies 13 Apr 2023 8/ Turning to the origin of variance, prior works (especially https://t.co/OsVeRFogKu) have observed that ensembles of independently trained networks make roughly calibrated predictions. I prove that this calibration property alone implies variation in test-set accuracy. https:// 7.3K views · 38 likes · 1 reposts · 1 replies 13 Apr 2023 7/ Also usefully, the excess observed variance over this statistical model forms an unbiased estimator for the variance in accuracy on the test _distribution_, which turns out to be very small. (Full definitions & proof in the paper) https://t.co/6kAUGN3Y24 5.6K views · 29 likes · 0 reposts · 2 replies 13 Apr 2023 6/ This would imply that the test-set accuracy distribution is generated as the sum of a series of independent coin flips, one for each test-set example. And…this simple statistical model actually turns out to be a very good approximation. https://t.co/RZmvJ0la0M 6K views · 52 likes · 1 reposts · 2 replies 13 Apr 2023 3/ However, it’s not yet clear if these lucky runs of training are actually better than unlucky ones. To find out, I split the CIFAR-10 test-set into two halves, and evaluated thousands of trained networks against both. Intuitively, lucky networks should do well on both splits. 7.4K views · 44 likes · 0 reposts · 1 replies 13 Apr 2023 5/ Given this lack of correlation between performance on splits of test-set data, I next test the hypothesis that there also aren’t even any correlations between individual examples. https://t.co/9ojxqNp1iq 6.2K views · 36 likes · 0 reposts · 1 replies 13 Apr 2023 4/ But instead, it turns out that by the end of training, there’s almost no correlation between performance on the two splits. For example, out of ~10^5 repeated trainings, the best network on the first split isn’t even above average on the second. https://t.co/ew74cE8tIw 7.7K views · 65 likes · 2 reposts · 2 replies 13 Apr 2023 2/ Background: for standard CIFAR-10 trainings there exist rare “lucky seeds/runs” attaining over +0.5% higher test-set accuracy than the average (10% fewer errors). ImageNet trainings are similar with +0.4%. These differences are considered significant in computer vision. 8.6K views · 55 likes · 0 reposts · 2 replies 13 Apr 2023 Neural network trainings are nondeterministic. Repeated runs each produce a unique network, often with significantly _varying_ test-set performance. 🆕📜 I demonstrate that this variation has a simple statistical structure, and is harmless & inevitable https://t.co/1zzpNHi0Vy 273.8K views · 1.3K likes · 160 reposts · 28 replies 13 Apr 2023 "torch.manual_seed(3407) is all you need"! draft 📜: https://t.co/MyLlhHPcsM Sorry for the title. I promise it's not (entirely) just for trolling. It's my little spare time project of this summer to investigate unaccounted randomness in #ComputerVision and #DeepLearning. 🧵👇 1/n 0 views · 402 likes · 79 reposts · 6 replies 25 Aug 2021

Similar accounts