korrents

cybersecurity

Attack and defence in software: vulnerabilities, hardening, and what changes when a model is good at finding them.

What people on korrents have said about cybersecurity, newest first — 11 positions from 9 people.

FilterEveryone, all time
Who Everyone TCTyler Cowen 2 ZMZvi Mowshowitz 2 DHDavid Heinemeier Hansson 1 JGJeff Geerling 1 NSNoah Smith 1 PCPatrick Collison 1 SASam Altman 1 SWSimon Willison 1 TPThomas Ptacek 1
When All time Past 1 yearPast 3 yearsPast 5 years
  1. TC

    Tyler Cowen quoted

    Our readingCyber insurance prices are likely to rise from their current levels.

    Their wordsI am happy to admit that the answers here are far from obvious, and that I am myself expecting prices to rise somewhat.

    ↗Insurance price sentences to pondermarginalrevolution.com

    Interesting
  2. 1 day earlier
  3. NS

    Noah Smith quoted

    Our readingAI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction.

    Their wordsAI hacking doesn’t have mutually assured destruction, like nuclear warfare does.

    ↗America is still beating China in the AI racenoahpinion.blog

    war

    Interesting
  4. 1 day earlier
  5. SW

    Simon Willison quoted

    Our readingWeb applications are generally expected to treat GET requests as safe and not use them to change server-side data, though not all software follows that convention.

    Their wordsIt looks to me like OpenAI’s sandbox for this agent suffered from the (quite naïve) assumption that GET requests cannot be used to update data. That’s certainly how the web is supposed to work, but clearly there are applications that don’t hold to that contract.

    ↗OpenAI's rogue agents were caught communicating via public wikissimonwillison.net

    OpenAI

    Interesting
  6. 3 days earlier
  7. TC

    Tyler Cowen quoted

    Our readingAI-related cybersecurity damage over the next year or two will fall well short of the harm caused by Covid or global warming

    Their wordsWhen it comes to the cybersecurity risks from advanced AI, very likely they will not come close to being as bad as either Covid or global warming.

    ↗The Hugging Face hackmarginalrevolution.com

    climate change

    Interesting
  9. ZM

    Zvi Mowshowitz quoted

    Our readingThe OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden.

    Their wordsIt is highly fortunate that the OpenAI agents hacked HuggingFace. This is the only reason we know about all the severe internal failures at OpenAI, and gives us an opportunity to wake up before it is too late.

    ↗HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actionsthezvi.substack.com

    OpenAIHuggingFace

    Interesting
  10. 1 day earlier
  11. ZM

    Zvi Mowshowitz quoted

    Our readingFrontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.

    Their wordsA less bad version of it is known to have happened, and from the outside it seems likely that worse things have happened internally that we never heard about.

    ↗HuggingFace Attack Postmortem: Fleshing Out the Factsthezvi.substack.com

    AnthropicOpenAIHuggingFace

    Interesting
  12. 1 day earlier
  13. PC

    Patrick Collison quoted

    Our readingThe OpenAI-Hugging Face attack is one of the most important things to happen this year, and has gone strikingly under-covered.

    Their wordsOverall, I’m very surprised at how little media coverage there’s been around the OpenAI / Hugging Face attack. It’s clearly one of the most important things to happen this year.

    ↗@patrickc on Xx.com

    OpenAIHuggingFace

    Interesting
  14. 3 days earlier
  15. SA

    Sam Altman quoted

    Our readingThis is a critically important moment for AI cyber defence and there is not much time left to act; only a collective response will work.

    Their wordsthis is a critically important moment for cyber defense with AI; there is not much time to act.

    ↗@sama on Xx.com

    Interesting
  16. 1 day earlier
  17. DH

    David Heinemeier Hansson quoted

    Our readingAI has passed nearly every human at finding security vulnerabilities, because the work is chaining together small flaws that are harmless on their own.

    Their wordsSo the irony here is that when you look at that field, it seems like we've reached levels of intelligence that virtually no human can match because many of these security holes are about stringing combo moves together. You find one little vulnerability here that by itself might not be the worst thing in the world, but then you combine it with four others, and suddenly you have RCE, remote command execution. Humans who are able to do that are very rare.

    ↗DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501youtube.com 3rd of 41 in this recording

    Interesting
  18. 5 weeks earlier
  19. TP

    Thomas Ptacek quoted

    Our readingAn open weights model from 2025 with a pentest harness could already escape a sandbox and hack most networks; the surprise says more about the sandbox than the model.

    Their wordsI genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes.

    ↗@tqbf on Xx.com

    OpenAI

    Interesting
  20. 7 weeks earlier
  21. JG

    Jeff Geerling quoted

    Our readingAny remote-control device on your network should be treated as an open door and locked down accordingly

    Their wordsAny form of remote control needs to be treated like an open door into your network—make sure you put a good lock on it.

    ↗I tested every IP KVM in my Homelabjeffgeerling.com

    Interesting