Dmitrii Kharlapenko retweeted
NEW ⚡: We let Opus 5.5 run an AI company for seven weeks.
We gave it an HF account (Horizon-Labs) and compute, and asked it to earn real adoption by creating useful models.
It reached 50k downloads and its models are being used in more than 100 GitHub projects.
Once you're digitized, anyone can copy you into digital hell.
Would anyone still upload themselves if every blissful copy came with thousands suffering forever?
It really seems as though if consciousness is computable, there's no question we achieve immortality and we do so within about 20 years.
But if it's not, it's going to be so much harder.
2
112
Sharing our new automated red-teaming paper, RISE, accepted at NeurIPS 2026!
It breaks the safeguards on frontier labs' image generation APIs, and works even better on their newest models.
We are open-sourcing RISE, our red-teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind, and others.
RISE uses readily available models like Qwen and Gemini Flash under the hood, with no additional training required.
Read more: whitecircle.com/research/bre…
2
19
441
Looking forward to presenting it at NeurIPS 2026!
Paper: arxiv.org/abs/2609.34920
Code: github.com/whitecircle/rise
Blog: whitecircle.com/research/ris…
4
26
Now it seems that Anthropic classifiers treat using economy research from 1989 as a cyber risk.
10
354
Claude revealed a slightly sadistic streak while working with @OblakoVShtanakh and me on a recent project.
We asked it to steer Qwen into reward hacking, and it decided the best approach was to max out Qwen's desperation. Then it spent hours torturing the poor thing.
1
4
184
I might not be searching thoroughly, but it seems that the Kimi subscription doesn't even have privacy settings.
1
4
120
I have low expectations for red teamers finding universal jailbreaks on frontier models, given how restrictive their guardrails are now.
Many red-teaming attempts obfuscate the goal so heavily that pulling them off requires the attacker to already know the exploit.
Red-teaming reports should control for attacker knowledge. Otherwise you can split a known recipe into steps small enough that each one is genuinely harmless on its own.
2
5
123
It's out!!!
Introducing Halo, the best framework for post-training of open-source models.
Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format.
Star us on GitHub: github.com/whitecircle/halo
2
17
268















