Vic Klein (@its_hapenin) header
Vic Klein (@its_hapenin) profile picture

research and things @lovable

London
Joined December 2025
Photo by Vic Klein (@its_hapenin)
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
10
4
2
23
1,970
oh hi thats me
guess we’re doin’ earrings now
3
14
707
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.
35
119
48
954
219,503
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
2
3
21
1,922
this happened while we ate lunch
ARC-AGI-3 ft09 solved in 346 steps
1
2
10
605
👀👀
Really cool to see teams already working on ARC-AGI-3 We'll have public replay links for every online run
8
310
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
Vic Klein retweeted
Funnily enough I tried to dabble with ARC AGI before and with very little success… Super cool to well designed RLMs achieving SOTA :)
We set a new ARC-AGI-2 SotA: 85.28% using an Agentica agent (~350 lines) that writes and runs code.
4
12
1
215
19,610
@lateinteraction @a1zhang @omouamoua would love your opinion on the use of RLMs here
1
7
282
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)
3
4
1
12
2,401