
Shlomie Liberow
1.5K posts

Shlomie Liberow
@Shlibness
Building https://t.co/FptvfrXME5 - Former Head of Hacker R&D @Hacker0x01. All things hacking!


Congratulations to the #H1-21 award winners! 🎉 Thank you for your incredible work in Lisbon. Your contributions help make the digital world safer for everyone.


WE DID IT ! WE RAISED $5.9M PRE-SEED 🥳🎉🎉




Brilliant move by @AnthropicAI to sponsor Claude ads on stacktraces that get no results


Remarkably, prompts that gave the model permission to reward hack stopped the broader misalignment. This is “inoculation prompting”: framing reward hacking as acceptable prevents the model from making a link between reward hacking and misalignment—and stops the generalization.

We disrupted a highly sophisticated AI-led espionage campaign. The attack targeted large tech companies, financial institutions, chemical manufacturing companies, and government agencies. We assess with high confidence that the threat actor was a Chinese state-sponsored group.














