Post

Thread about claims like "OpenAI should have just sandboxed the agents better" "OpenAI shouldn't have run the agents with the anti-hacking guardrails off" (so many articles are making these points that I'm not going to bother linking)

A. H. Zakai

@kripken.com

On sandboxing: I've worked in the web browser field for 16 years. Browsers like Chrome, Firefox, and Safari have large, well-funded teams of some of the best engineers on the planet, but their sandboxes still get exploited by humans. LLMs are even better. "Just sandbox better" isn't enough.

A. H. Zakai

@kripken.com

On "why did they disable the anti-hacking safeguards?": for very good reason. This is how browsers etc. are made secure, by using LLMs to find exploits before the bad guys do: blog.mozilla.org/en/firefox/p...

blog.mozilla.orgThe zero-days are numbered | The Mozilla BlogSince February, the Firefox team has been working around the clock using frontier AI models to find and fix latent security vulnerabilities in the browser.

A. H. Zakai

@kripken.com

Running LLMs without anti-hacking safeguards is standard practice and absolutely necessary. Defenders *must* do this, because attackers certainly are - using open models, or jailbroken ones, or their own.

27/9/26, 5:14 pm0 reposts0 likes

A. H. Zakai

@kripken.com

If you used a web browser today, you used software that was more secure thanks to LLMs running without safeguards.

A. H. Zakai

@kripken.com

OpenAI certainly made mistakes, and this removes none of their responsibility. But some people think that if we just used LLMs in some safe way, everything would be fine. There is no such option. This technology is extremely capable, and not entirely predictable.