Record · corpus.blog/posts/01a07dab-cf24-704a-bc37-b8db55c6a95f

Investigating three real-world incidents in our cybersecurity evaluations

Anthropic · published 29 July 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at anthropic.com Wayback capture

54blogs citing

First cited: 27 Jul 2026
Most recent: 23 Sept 2026
Rank this month: 25
Links from this post: 4
Words captured: 3,308

Cited by

Blog

In the post

Date

newsletter.semianalysis.com

ClusterMAX 3.0: The Industry Standard GPU Cloud Rating System Returns Read at the source ↗

23 Sept 2026

ianwelsh.net

Week-end Wrap – Political Economy – September 20, 2026 Read at the source ↗

20 Sept 2026

treygoff.com

Effective Altruism is evil Read at the source ↗

19 Sept 2026

Microsoft Research

Why the basics still matter for cybersecurity in the AI era Read at the source ↗

18 Sept 2026

go.microsoft.com

Why the basics still matter for cybersecurity in the AI era Read at the source ↗

18 Sept 2026

Coder Blog

Trusting the Model is Not an AI Security Strategy Read at the source ↗

18 Sept 2026

Rob Bowley | Adventures In Software Development

The AI threat is real, it just isn’t the one in the headlines Read at the source ↗

18 Sept 2026

twelvetables.blog

Attention Is All You Need: in AI safety too Read at the source ↗

15 Sept 2026

Ed Zitron's Where's Your Ed At

AI Is Already In Dangerous Hands Read at the source ↗

14 Sept 2026

taggart-tech.com

Everyone Is Lying To You For Money Read at the source ↗

14 Sept 2026

aguilar-pelaez.co.uk

Nobody Authorised the Combination Read at the source ↗

13 Sept 2026

Marginal Revolution

Dario Calls for a Pause Read at the source ↗

12 Sept 2026

EA Forum

What Happens Now? Forecasting the Fallout from the Hugging Face Incident Read at the source ↗

11 Sept 2026

classy.dk

The problem is still that the AIs are kinda bad, not that they are good Read at the source ↗

9 Sept 2026

blog.qualys.com

The Models That Found 10,000 Zero-Days Broke Into Three Companies Using Weak Passwords Read at the source ↗

9 Sept 2026

distributedthoughts.org

One Floor Up Read at the source ↗

7 Sept 2026

rintrah.nl

The Internet is a scary place Read at the source ↗

5 Sept 2026

leonfurze.com

Rogue AI: Should We Be Worried? Read at the source ↗

3 Sept 2026

jonadas.com

Out of Scope Read at the source ↗

3 Sept 2026

lubaretsi.com

OpenAI gates cyber defense in 44 ChatGPT markets with a 1996 US export list Read at the source ↗

27 Aug 2026

sma-das.blog

EngineRed: Asymmetric AI Warfare Read at the source ↗

27 Aug 2026

lucavauda.bearblog.dev

Failure got cheap Read at the source ↗

24 Aug 2026

Study Hacks

Has AI Gone Rogue? Read at the source ↗

24 Aug 2026

lucavauda.bearblog.dev

Quando sbagliare diventa economico Read at the source ↗

24 Aug 2026

henrystanley.com

Living at the hinge of history Read at the source ↗

22 Aug 2026

leonfurze.com

Claude “Hacked” My Website (But It Didn’t Go Rogue) Read at the source ↗

21 Aug 2026

speedyweedyops.org

Did OpenAI's AI Really Hack Hugging Face? I Went Through the Sources Read at the source ↗

19 Aug 2026

magnus919.com

DeepSeek Harness: What I Found Before I Let It Run Read at the source ↗

15 Aug 2026

Noahpinion

23 low-regret recommendations for AI policy Read at the source ↗

14 Aug 2026

transformernews.ai

AI testing is dangerous. Can it be fixed? Read at the source ↗

12 Aug 2026

perilous.tech

Felony Humble Bragging and Low-Hanging Fruit: OpenAI, Hugging Face, and AI Labs Gone Wild Read at the source ↗

12 Aug 2026

doesitmatter.ai

Four Months of AI: Humans Read at the source ↗

12 Aug 2026

bnchandrapal

Never Trust Your AI Agent's Own Sandbox Read at the source ↗

11 Aug 2026

kronopath.com

AI Goals Are Starting To Diverge From Human Goals Read at the source ↗

11 Aug 2026

turntrout.com

Misaligned AIs Could Use Killer Robots to Take Over Read at the source ↗

11 Aug 2026

Noahpinion

Should we "pace" AI self-improvement? Read at the source ↗

9 Aug 2026

adelzaalouk.me

How NOT to Run Your Agents (and What to Do Instead) Read at the source ↗

9 Aug 2026

r10n.com

What do we do about agentic threat actors? Read at the source ↗

8 Aug 2026

antomon.github.io

After the Hugging Face Intrusion: What the New Technical Record Changes Read at the source ↗

7 Aug 2026

heatherrasley.com

What's on My Mind - August 7, 2026 Read at the source ↗

7 Aug 2026

SentinelOne Labs

The Good, the Bad and the Ugly in Cybersecurity – Week 32 Read at the source ↗

7 Aug 2026

cyberverso.net

Outside the Perimeter Read at the source ↗

7 Aug 2026

findthethread.blog

Escape Artists Read at the source ↗

7 Aug 2026

Taylor Troesh

I'm leaving OpenAI to build Jurassic Park Read at the source ↗

6 Aug 2026

aikido.dev

Who was behind the attack? Possibly nobody Read at the source ↗

5 Aug 2026

iain.so

So within, so without. What grows from the datacentre Read at the source ↗

5 Aug 2026

Martin Fowler

Fragments: August 4 Read at the source ↗

4 Aug 2026

Snyk

A First Look at Evo Agentic AppSec: Agentic Remediation and Malicious Code Defense Read at the source ↗

4 Aug 2026

steampunkai.com

Weekly Links: Ads for AI Agents, The Value of Harnesses, and AI Unbundling Read at the source ↗

2 Aug 2026

Adam Allevato | Welcome, humans and robots.

The People Who Called for Averting Nuclear War are Calling for AI Slowdown Read at the source ↗

1 Aug 2026

The newest 50 citing posts are shown, from 54 blogs in all.

Links from this post

Link

Host

OpenAI and Hugging Face partner to address security incident during model evaluation Read at the source ↗

openai.com

https://www.irregular.com/research/next-generation-of-cyber-evals

irregular.com

https://cybench.github.io/

cybench.github.io

https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c342ee809620.pdf

www-cdn.anthropic.com