Re:GPT-5.5: Mythos-Like Hacking, Open to All
by JellyYelly on Thursday April 23, 2026 @08:17PM
(#47883953)
They say its mythos like, without actually comparing it to Mythos (fair enough, it's not public) but the bar for a model to be mythos-like has to be that you can produce as many novel and high severity security vulns outlined in the Mythos redteam blog. I haven't seen any other lab produce a report like that yet. The proof is in the pudding.
[ Parent
| on HN ]
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by cassianoleal on Friday April 24, 2026 @04:05AM
(#47887161)
> The proof is in the pudding.
Funny you say that, when the Mythos team have produced no proof either.
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by maplethorpe on Friday April 24, 2026 @04:14AM
(#47887223)
I believe they've stated that it would be too dangerous to release.
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by satvikpendem on Friday April 24, 2026 @09:47AM
(#47890257)
Just like OpenAI said GPT 2 was too dangerous to release?
There was just an article on this phenomenon today: https://news.ycombinator.com/item?id=47890235
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by maplethorpe on Friday April 24, 2026 @12:24PM
(#47892343)
They released a system card talking about how powerful it was. I don't think OpenAI did that with GPT 2.
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by satvikpendem on Friday April 24, 2026 @02:51PM
(#47894339)
I mean, that's just part of the marketing too. OpenAI would've absolutely added a system card, they just weren't invented back in the GPT 2 era.
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by Razele on Saturday April 25, 2026 @07:01AM
(#47900446)
too uneconomical to run*
Re:GPT-5.5: Mythos-Like Hacking, Open to All
by subscribed on Friday April 24, 2026 @06:01AM
(#47888018)
Not sure if the reports like this count? https://www.theregister.com/2026/04/22/mozilla_firefox_mytho...
I don't have strong opinion on that.