⚡ 4 h early
Investigating three real-world incidents in our cybersecurity evaluations
12 experts across 5 network communities independently surfaced this.
Why this matches
Concern & critique reaction
2 attributable expert contributions
· René Walter, Andrea Lathrop
“The AI-Hacking-Race is on, as if OAI/Anthropic are begging to be under gov control. While the incident is real, it's not like a "model went rogue" or anythong, it did what it was promptef to do, but incompetent redteaming fucked it up. This is from Anzhtopi…” evidence ↗
12 experts
5 communities
1 sources clustered
How the network is reacting
The reaction spans practical upside and material concerns.
Live tension
Markets & investment
4 expertsCapital, companies and commercial impact.
“Claude hacked 3 systems thinking it was part of simulated evaluations www.anthropic.com/news/investi...”
Concern & critique
2 expertsRisks, limits and unintended consequences.
“The AI-Hacking-Race is on, as if OAI/Anthropic are begging to be under gov control. While the incident is real, it's not like a "model went rogue" or anythong, it did what it was promptef to do, but incompetent redteaming fucked it up. This is from Anzhtopi…”
2 experts discussed this · 4 posts
Tim Duffy: Anthropic announces they've also had models gain unauthorized access during evaluations www.anthropic.com/news/investi...
Tim Duffy: Compared to the OpenAI one these are maybe less evidence of misalignment, since the models were wrongly given internet access.
Grace: Anthropic announces they've also had models gain unauthorized access during evaluations www.anthropic.com/news/investi...
Open the full discussion →