Greg Kamradt ✓
@GregKamradt · San Francisco, CA · joined 18 Jan 2011
President @arcprize, builder/engineer
50 915Followers
1 027Following
10 297Posts total
496.9KViews on collected posts
Postingan terbaru
Mencari postingan baru…
Wow I’ve been wondering which team was in first
They were using a code name until today
Turns out it was @aimalysheva and crew https://t.co/m4ZWRvpCXi
15.2K views · 143 likes
· 5 reposts · 4 replies
Open on X →
.@NickWentz_ @MatthewBerman @angela_ferrante crushing tonight https://t.co/0i8VGAUNel
3K views · 18 likes
· 1 reposts · 3 replies
Open on X →
@GregKamradt this is simply a fail. it is dishonest for anyone benchmarking these user-hostile models to pretend otherwise. "here's the hypothetical score it would have gotten if it actually worked" is absolute fraud.
541 views · 34 likes
· 1 reposts · 0 replies
Open on X →
rereading my post I don't give enough credit to our anthropic contact
they (renmaing nameless) is great and fights for us internally. It's a big org which requires navigation and we're thankful for their help.
2.3K views · 42 likes
· 0 reposts · 0 replies
Open on X →
During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as "reverse engineering"
We were in contact with the Anthropic team the whole time and they tried to lift the restrictions in time for launch but
49.7K views · 250 likes
· 19 reposts · 31 replies
Open on X →
Fable 5.1 from @AnthropicAI on ARC-AGI (Verified):
- ARC-AGI-2: 90.0%, $3.12/task
- ARC-AGI-1: 97.5%, $1.40/task
Across the two benchmarks, Fable 5.1's average cost per task is about 32% lower than Fable 5's, driven by better token efficiency. https://t.co/WgkmPbnPrT
122.7K views · 845 likes
· 38 reposts · 34 replies
Open on X →
Emergency Grok @bot meetup, 9/1 in SF
Come join
Cohosting with @MatthewBerman @NickWentz_ & Angela Ferrante
@kristaletz and @AlexFinn are going to demo what they're excited about
$100 Grok Bot credits onsite - thank you @SpaceXAI!
https://t.co/b1E1FioOiO
38K views · 75 likes
· 6 reposts · 8 replies
Open on X →
@GregKamradt @botxtraderz Can you provide the sample size, distribution and features for human testing? How was the 100% result reached? The lack of human datasets is a major concern in your tests.
5.6K views · 46 likes
· 1 reposts · 2 replies
Open on X →
ARC-AGI-3 is an important benchmark. However, I have a major issue with the “Human score 100%” statement. How many humans have tested all 1000 puzzles? How were people selected? This was not published for previous ARCs either. In one case, the human score was based on I think 2
39.6K views · 274 likes
· 22 reposts · 54 replies
Open on X →
Go play the games and build agents
https://t.co/PLAKaIii8k https://t.co/KhF3Ad7aH3
4.2K views · 40 likes
· 4 reposts · 0 replies
Open on X →
Today we're launching ARC-AGI-3
135 Novel Environments (nearly 1K levels) we build by hand
It is the only unsaturated agent benchmark in the world
Each game is 100% human solvable, AI scores <1%
This gap between human and AI performance proves we do not have AGI
Agents today
212.5K views · 855 likes
· 86 reposts · 97 replies
Open on X →
Dibandingkan akun berukuran sama
8 postingan dari 90 hari terakhir, dibandingkan dengan rentang 10K–100K pengikut. tampil luas, tetapi sedikit penonton yang merespons.
Median tayangan9 271akun ini924median untuk 10K–100K
Jangkauan, %18.21%akun ini3.62%median untuk 10K–100K
Interaksi, %0.77%akun ini1.52%median untuk 10K–100K
| Metrik | Akun ini | Median untuk 10K–100K | Rasio |
|---|---|---|---|
| Median tayangan per postingan | 9 271 | 924 | 10.0× |
| Jangkauan (tayangan ÷ pengikut) | 18.21% | 3.62% | 5.03× |
| Tingkat interaksi | 0.77% | 1.52% | 0.51× |
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
212.5K25 Mar
4.2K
39.6K
5.6K
38K24 Aug
122.7K1 Sep
49.7K
2.3K
5412 Sep
3K
3.3K
15.2K3 Sep
Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.51%25 Mar
1.07%
0.90%
0.88%
0.25%24 Aug
0.76%1 Sep
0.62%
1.79%
6.47%2 Sep
0.79%
0.45%
1.00%3 Sep
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes75.1%2 635 in total
Reposts5.2%184 in total
Replies6.7%234 in total
Quotes2.0%70 in total
Bookmarks11.0%386 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.
Akun serupa
Eugenio Tironi
@eugeniotironi
101.8K followers
· 11.5K posts
Radical Rhymes
@RhymesRadical
101.8K followers
· 164.7K posts
El Anillo Único ✓
@ElAnilloUnico
101.8K followers
· 38.7K posts
Fernando Cao ✓
@thefernandocz
101.8K followers
· 18.2K posts
Koen Bok ✓
@koenbok
101.8K followers
· 12K posts
The Eggman
@ASleepyEgg
101.8K followers
· 9.1K posts
PROOF ✓
@proof_xyz
101.8K followers
· 3K posts
Sam Curry ✓
@samwcyo
101.8K followers
· 3.1K posts