
Pinned Tweet
I’ve been working on ARC-AGI-2 and the best part of this for me was seeing how different models behaved, how they worked it out and when they didn’t. You can see the logs here. Thanks to @fchollet for the challenge. symbolica.ai/blog/arcgentica
it’s been great building the @agenticasdk and getting it do some interesting things. i’ll be moving on and am excited for what’s to come. thank you to everyone i’ve worked with.
2
6
303
Vic Klein retweeted
Introducing Mixedbread Wholembed v3, our new SOTA retrieval model across all modalities and 100+ languages.
Wholembed v3 brings best-in-class search to text, audio, images, PDFs, videos...
You can now get the best retrieval performance on your data, no matter its format.
Vic Klein retweeted
We've released the code used to solve all 3 publicly available ARC-AGI-3 games.
github.com/symbolica-ai/ARC-…
Vic Klein retweeted
Join us this Thursday, 26th in London.
We’ll be speaking about ARC-AGI-2 and ARC-AGI-3 at the London AI nerd meetup: what’s new, what’s changing, and what it means for agents.
@its_hapenin @FireworksAI_HQ
luma.com/z4i401h6
If you’re interested :)
Vic (@its_hapenin) will chat ARC-AGI-2 results at Engineering Night London - what worked, what didn’t, and what surprised us.
With Agentica:
• 85.28% with Opus 4.6 (120k) High
• +10pp GPT-5.2 (XHigh) vs CoT
• +20pp Opus 4.5 vs CoT
See you there.
Register: luma.com/w5keu427
2
6
365
You can see the logs for Opus 4.6 here: github.com/symbolica-ai/arcg…
6
332
i wrote a thing with @charlielidbury, because agents want an execution environment symbolica.ai/blog/beyond-cod… (we built it too)










