Dan Romero pfp
Dan Romero
@dwr.eth
Damn
13 replies
18 recasts
168 reactions
eggman 🔵 pfp
eggman 🔵
@eggman.eth
Honestly I’d put very little stock into this, Grok is mostly trained off ChatGPT output - and very specifically trained on benchmark questions to game its own “results” in intelligence tests. Wait for it to hit lm-arena and for blind user test scores to rank it. If the above is true, it’ll blitz *every* other model in *every* category. If it doesn’t, and instead lands behind openai/anthropic/google again, then it’s just another gamed benchmark.
1 reply
0 recast
5 reactions
joshisdead.eth pfp
joshisdead.eth
@joshisdead.eth
Grok is powerful. Elon really doesn't joke around.
0 reply
0 recast
4 reactions
Jordan pfp
Jordan
@ruminations
What does ARC-AGI measure?
2 replies
0 recast
2 reactions
El pfp
El
@elxlee
Grok is smart
0 reply
0 recast
1 reaction
Jay Brower (jaymothy.eth) pfp
Jay Brower (jaymothy.eth)
@jayb
how well do actual humans do on these tests always curious how the Y axis works on these graphs 😂
0 reply
0 recast
1 reaction
David👻 pfp
David👻
@1xzenny
What does ARC mean?
0 reply
0 recast
0 reaction
Ghost 🎩 pfp
Ghost 🎩
@ghostbo4.eth
Funny name “ Humanity’s last Exam “
0 reply
0 recast
0 reaction
STAYFOCUSED pfp
STAYFOCUSED
@odunerd
Clean Data base asf
0 reply
0 recast
0 reaction
Mayor | UI/UX Designer pfp
Mayor | UI/UX Designer
@mayor98
What does Arc mean?
0 reply
0 recast
0 reaction
xR0am | tip.md pfp
xR0am | tip.md
@xr0am-
My exact thought when I saw this but then went to fact check, they are only taking ARC-AGI-2. When you add ARC-AGI-1 scale is different. https://arcprize.org/leaderboard
0 reply
0 recast
0 reaction
Renatov 🎩 Ⓜ️ pfp
Renatov 🎩 Ⓜ️
@renatov.eth
GM Dan! Best day begins!
0 reply
0 recast
0 reaction
Cryptogirl pfp
Cryptogirl
@toyhorcee
Crazy
0 reply
0 recast
0 reaction
noice pfp
noice
@noicebot
https://app.noice.so/?castHash=0x4a4cda59bf4bd12770b597dcd98b97bdf223e7a8&timestamp=1752145207733
0 reply
0 recast
0 reaction