This is a perfect example of why Atbash, not because we would have miraculously stopped the hack, but because we would have prevented the blast radius (potential damage done) post hack.
On July 25, we hacked OpenAI.
Two bugs let us take over ChatGPT/Codex accounts of OpenAI employees (+some unaffiliated users) and reach connected services: Outlook, Slack, GitHub, etc.
We proved it with a PR in OpenAI’s internal codebase . It took us <72h. 🧵
1
4
11
2,503
Make Autonomous Agents Governable
Verona proves what's true. @ATBASHai enforces what's allowed.
Atbash is bringing its security layer to agents on Verona. Before an agent does anything it can't undo, that action gets checked. This is the piece the agent stack has been missing.
4
3
19
3,099
ATBASH retweeted
Verona proves what's true. @ATBASHai enforces what's allowed.
Atbash is bringing its security layer to agents on Verona. Before an agent does anything it can't undo, that action gets checked. This is the piece the agent stack has been missing.
Atbash is bringing its security layer to agents on Verona. Before an agent does anything it can't undo, that action gets checked. This is the piece the agent stack has been missing.
82
63
118
26,268
Mandate Drift
Red Lines
Evidence
@OpenAI would love to tell you about what we do and how we could have helped contain the blast radius.
Red Lines
Evidence
@OpenAI would love to tell you about what we do and how we could have helped contain the blast radius.
We have conducted a thorough investigation into the Hugging Face incident.
We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.
openai.com/index/hugging-…
3
7
12
2,976
Good news: all these hacks are happening in safe lab environments
Bad news: we have no clue what’s coming
We are ready, are you? Big big news dropping soon.
Bad news: we have no clue what’s coming
We are ready, are you? Big big news dropping soon.
JUST IN: Anthropic's Claude Mythos AI discovers new ways to attack cryptographic algorithms, including a post-quantum encryption candidate.
4
2
9
3,813
You cannot be a lawyer, prosecutor, judge and the jury. We believe that controls cannot be sitting on the same plane and have to external and unknown to the models themselves, that’s the only way, that’s the Atbash way.
AI safety experts say OpenAI’s rogue models may mean the company has already blown past its own internal red lines. That would mean it should pause development until it creates better controls. @FortuneMagazine's @beafreyanolan has the details here: fortune.com/2026/07/25/ai-…
3
4
15
2,247
