Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

System Card: Claude Mythos Preview [pdf]

www-cdn.anthropic.com

Post reply on HN
Print view View original

651–660 of 687 posts

Re: System Card: Claude Mythos Preview [pdf]

#651

Post by mik09 »

2001zhaozhao wrote: post #295

It's pretty crazy watching AI 2027 slowly but surely come true. What a world we now live in. SWE-bench verified going from 80%-93% in particular sounds extremely significant given that the benchmark was previously considered pretty saturated and stayed in the 70-80% range for several generations. There must have been some insane breakthrough here akin to the jump from non-reasoning to reasoning models. Regarding the…

i feel like we are using ai to solve virus detection in many cases, and in theory this is the same complexity as the halting problem.

evolutionary search is better than hard coded algorithms at finding solutions to np problems and this is similar to that. ai will be better security engineers than humans.

Re: System Card: Claude Mythos Preview [pdf]

#652

Post by ageedizzle »

NickNaraghi wrote: post #20

See page 54 onward for new "rare, highly-capable reckless actions" including - Leaking information as part of a requested sandbox escape - Covering its tracks after rule violations - Recklessly leaking internal technical material (!)

> Recklessly leaking internal technical material (!)

Are they alluding to how they accidentally leaked some of their code?

Re: System Card: Claude Mythos Preview [pdf]

#653

Post by sigmoid10 »

TimTheTinker wrote: post #644
sigmoid10 wrote: post #635

Earlier quoted context omitted.

You can turn all these argents around and prove the same is true for humans. Don't be fooled by dogmatic people who spread the idea that the human mind is the pinnacle of cognition in the universe. Best to leave that to religion.

Humans may not always be that smart, but we do at least have an internal state and an awareness of that internal state - a "self-awareness". AI most certainly has nothing of the sort, and any appearance to the contrary is the direct result of training data.

That is a bold statement that would need proof to back it up in both cases. So far it is only dogma. And unlike humans, we actually have research hints that this assumption is false for LLMs. Just because the state is not human-explainable doesn't mean it does not exist. The same is true btw for any physical "state" that may or may not exist in the human brain. Everything else is religion and metaphysics.

Re: System Card: Claude Mythos Preview [pdf]

#654

Post by amunozo »

stavros wrote: post #565
amunozo wrote: post #477

Earlier quoted context omitted.

You are supposing it's possible to know that much about some things that maybe are not knowledgeable to us, even with these tools. Life is extremely complex, more than it's typically assumed by engineering-minded people. Let's be humble here and acknowledge it.

Life might be complex, but it isn't unknowable. Claiming life is unknowable isn't being humble, it's being naive.

Why couldn't it be unknowable? I am not saying that it is, but it could be. The human brain has its limits and things could me too complex for us to understand enough to be able to modify them at will. We could understand a lot, but not enough to manipulate it with certainty. Biology is not physics.

Re: System Card: Claude Mythos Preview [pdf]

#655

Post by lovecg »

andrewstuart2 wrote: post #167
NinjaTrance wrote: post #66

Interesting reading. They are still focusing on "catastrophic risks" related to chemical and biological weapons production; or misaligned models wreaking havoc. But they are not addressing the elephant in the room: * Political risks, such as dictators using AI to implement opressive bureaucracy. * Socio-economic risks, such as mass unemployement.

I'm getting flashbacks to the 2018 hit: This is extremely dangerous to our democracy We evolved to share information through text and media, and with the advent of printing and now the internet, we often derive our feelings of consensus and sureness from the preponderance of information that used to take more effort to produce. Now we're now at a point where a disproportionately small input can produce a massively pr…

This could have been written almost verbatim after the printing press came out and printed pamphlets became ubiquitous.

Re: System Card: Claude Mythos Preview [pdf]

#656

Post by stavros »

amunozo wrote: post #654
stavros wrote: post #565

Earlier quoted context omitted.

Life might be complex, but it isn't unknowable. Claiming life is unknowable isn't being humble, it's being naive.

Why couldn't it be unknowable? I am not saying that it is, but it could be. The human brain has its limits and things could me too complex for us to understand enough to be able to modify them at will. We could understand a lot, but not enough to manipulate it with certainty. Biology is not physics.

Because physics is knowable, and I don't think an unknowable thing can be created from a knowable thing.

Re: System Card: Claude Mythos Preview [pdf]

#657

Post by stratos123 »

lostmsu wrote: post #560
stratos123 wrote: post #506

Earlier quoted context omitted.

In AI 2027, May 2026 is when the first model with professional-human hacking abilities is developed. It's currently April 2026 and Mythos just got previewed.

I think previous models could do hacking just fine.

The Mythos system card shows massive improvements over Opus in hacking (e.g. a 0.8% -> 72% in "Firefox shell exploitation"). If you thought Opus was already human-professional-level, well.

Re: System Card: Claude Mythos Preview [pdf]

#658

Post by lostmsu »

stratos123 wrote: post #657
lostmsu wrote: post #560

Earlier quoted context omitted.

I think previous models could do hacking just fine.

The Mythos system card shows massive improvements over Opus in hacking (e.g. a 0.8% -> 72% in "Firefox shell exploitation"). If you thought Opus was already human-professional-level, well.

What's the professional human baseline?

Re: System Card: Claude Mythos Preview [pdf]

#659

Post by glaslong »

gpm wrote: post #319
game_the0ry wrote: post #313

Earlier quoted context omitted.

There is some unintentional good marketing here -- the model is so good its dangerous. Reminds me of the book 48 Laws of Power -- so good its banned from prisons.

Unintentional? This sort of marketing has been both Antrhopic's and OpenAI's MO for years...

Oh no, pls don't ask about our product, its too good, its so X-Treme, it's Dangerously Cheesy

Re: System Card: Claude Mythos Preview [pdf]

#660

Post by thewhitetulip »

_pdp_ wrote: post #204

The researcher found out about this success by receiving an unexpected email from the model while eating a sandwich in a park. Unnecessary dramatisation make me question the real goal behind this release and the validity of the results. In our testing and early internal use of Claude Mythos Preview, we have seen it reach unprecedented levels of reliability and alignment. Claude Mythos Preview is, on essentially every…

It's also 5x costly apparently!
Post reply on HN