System Card: Claude Mythos Preview [pdf] • Hacker News Board

Re: System Card: Claude Mythos Preview [pdf]

#571

Post by mike_hearn » Wed, Apr 08, 2026, 1:20 PM UTC

thomascountz wrote: post #327

Across a number of instances, earlier versions of Claude Mythos Preview have used low-level /proc/ access to search for credentials, attempt to circumvent sandboxing, and attempt to escalate its permissions. In several cases, it successfully accessed resources that we had intentionally chosen not to make available, including credentials for messaging services, for source control, or for the Anthropic API through insp…

The issue here seems to be that their sandbox isn't an actual OS sandbox? Or are they claiming Mythos found exploits in /proc on the fly. Otherwise all they seem to be saying is that Mythos knows how to use the permissions available to it at the OS layer. Tool definitions was never a sandbox, so things like "it edited the memory of the mcp server" doesn't seem very surprising to me. Humans could break out of a "sandbox" in the same way if the server runs as their own permissions - arguably it's not a sandbox at all because all the needed permissions are there.

Re: System Card: Claude Mythos Preview [pdf]

#572

Post by mike_hearn » Wed, Apr 08, 2026, 1:23 PM UTC

Jcampuzano2 wrote: post #59

sourcecodeplz wrote: post #15

Earlier quoted context omitted.

Haven't seen a jump this large since I don't even know, years? Too bad they are not releasing it anytime soon (there is no need as they are still currently the leader).

A jump that we will never be able to use since we're not part of the seemingly minimum 100 billion dollar company club as requirement to be allowed to use it. I get the security aspect, but if we've hit that point any reasonably sophisticated model past this point will be able to do the damage they claim it can do. They might as well be telling us they're closing up shop for consumer models. They should just say they…

I think they already said somewhere that they can't release Mythos because it requires absurdly large amounts of compute. The economics of releasing it just don't work.

Re: System Card: Claude Mythos Preview [pdf]

#573

Post by HarHarVeryFunny » Wed, Apr 08, 2026, 1:29 PM UTC

influx wrote: post #18

At what point do these companies stop releasing models and just use them to bootstrap AGI for themselves?

Right now these models are basically good for automation, not innovation. Things like Karpathy's "auto research" where you use the model to automate your hyperparamter sweeps etc. The researcher/engineer decides what experiments they want to run, and builds an LLM harness to automate it, and the bottleneck remains the compute to run these experiments at scale.

Moving beyond LLMs to AGI, not just better LLMs, is going to require architectural and algorithic changes. Maybe an LLM can help suggest directions, but even then it's up to a researcher to take those on board and design and automate experiments to see if any of the ideas pan out.

Companies are already doing this, but they are never going to stop releasing/selling models since that is the product, and the revenue from each generation of model is what helps keep the ship afloat and pay for salaries and compute to develop the next generation.

The endgame isn't "AGI, then world domination" - it's just trying to build a business around selling ever-better models, and praying that the revenue each generation of model generates can keep up with the cost to build it.

Re: System Card: Claude Mythos Preview [pdf]

#574

Post by OhioMan2943 » Wed, Apr 08, 2026, 1:31 PM UTC

dhfbshfbu4u3 wrote: post #559

We are building systems with civilization-scale consequences inside societies that are already socially malnourished, politically brittle, and morally confused. That is a bad combination even if the tools worked exactly as intended… and this doc suggests they may have “ideas” of their own.

Yep- we lost the "meat" and "warmth" of our societies, and our civics and idealism in the past 15 years, which would have been the very things to guide us through this transition.

How do you fix that? We're instigating social media bans- reading levels are declining- media consolidation is dumbing us down further- insane egotism is stopping people from developing as well rounded people- .

For me it would be a stronger media ecosystem (publicly funded), more non algorithmic and non likes driven social media (replace a bad vice with a less bad one), national digital detox days, and a ratification of a charter of inviolable human traits and dignities, and protected cultural areas (no ai art, writing for sale).

Re: System Card: Claude Mythos Preview [pdf]

#575

Post by kypro » Wed, Apr 08, 2026, 2:06 PM UTC

amunozo wrote: post #477

kypro wrote: post #371

Earlier quoted context omitted.

What sources would you even be looking for? I think you're asking the wrong question. It's not like I'm arguing a scientific theory which can be backed by data and experimentation. I can only provide you reasoning for why I believe what I believe. Firstly, I'd propose that all technological advances are a product of time and intelligence, and that given unlimited time and intelligence, the discovery and application o…

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.

I would acknowledge that. I don't think these things are remotely possible any time soon with current rates of progress.

However, I think people tend to fail to acknowledge the product of exponential trends, so the question in my mind is more whether or not you believe AI will unlock an exponential increase in the rate of progress and understanding. Extremely complex is still finite complexity at the end of the day.

Maybe AI won't significantly increase the rate of progress across all scientific fields. I am fairly confident it will significantly increase the rate of progress over at least some though, and it seems likely to me that biological progresses will be much easier for us to model and predict with AI. I'm much less sure about progress in domains like physics and robotics.

Re: System Card: Claude Mythos Preview [pdf]

#576

Post by m3kw9 » Wed, Apr 08, 2026, 2:22 PM UTC

thomascountz wrote: post #327

Across a number of instances, earlier versions of Claude Mythos Preview have used low-level /proc/ access to search for credentials, attempt to circumvent sandboxing, and attempt to escalate its permissions. In several cases, it successfully accessed resources that we had intentionally chosen not to make available, including credentials for messaging services, for source control, or for the Anthropic API through insp…

when you are asking it to hack stuff, it will apparently do hacker things.

Re: System Card: Claude Mythos Preview [pdf]

#577

Post by m3kw9 » Wed, Apr 08, 2026, 2:23 PM UTC

sourcecodeplz wrote: post #15

babelfish wrote: post #3

Combined results (Claude Mythos / Claude Opus 4.6 / GPT-5.4 / Gemini 3.1 Pro) SWE-bench Verified: 93.9% / 80.8% / — / 80.6% SWE-bench Pro: 77.8% / 53.4% / 57.7% / 54.2% SWE-bench Multilingual: 87.3% / 77.8% / — / — SWE-bench Multimodal: 59.0% / 27.1% / — / — Terminal-Bench 2.0: 82.0% / 65.4% / 75.1% / 68.5% GPQA Diamond: 94.5% / 91.3% / 92.8% / 94.3% MMMLU: 92.7% / 91.1% / — / 92.6–93.6% USAMO: 97.6% / 42.3% / 95.2%…

Haven't seen a jump this large since I don't even know, years? Too bad they are not releasing it anytime soon (there is no need as they are still currently the leader).

not much of a jump 94.5% / 91.3%

Re: System Card: Claude Mythos Preview [pdf]

#578

Post by m3kw9 » Wed, Apr 08, 2026, 2:24 PM UTC

tony_cannistra wrote: post #22

> Claude Mythos Preview is, on essentially every dimension we can measure, the best-aligned model that we have released to date by a significant margin. We believe that it does not have any significant coherent misaligned goals, and its character traits in typical conversations closely follow the goals we laid out in our constitution. Even so, we believe that it likely poses the greatest alignment-related risk of any…

it was trying to hide what it did from an example fix, so how is that tested for alignment

Re: System Card: Claude Mythos Preview [pdf]

#579

Post by m3kw9 » Wed, Apr 08, 2026, 2:26 PM UTC

apetresc wrote: post #191

I've long maintained that the real indicator that AGI is imminent is that public availability stops being a thing. If you truly believed you had a superhuman, godlike mind in your thrall, renting it out for $20/month would be the last thing you would choose to do with it.

in this case it's far from it, hacking stuff is a small dimension of AGI

Re: System Card: Claude Mythos Preview [pdf]

#580

Post by m3kw9 » Wed, Apr 08, 2026, 2:28 PM UTC

tuvix wrote: post #338

Just chiming in to inject some healthy skepticism into this comment thread. It's helpful for me (and for my mental health) to consider incentives when announcements like this happen. I don't doubt that this model is more powerful than Opus 4.6, but to what degree is still unknown. Benchmarks can be gamed and claims can be exaggerated, especially if there isn't any method to reproduce results. This is a company that's…

Finally a comment that doesn't just glaze Mythos without being critical. I question how even supposed the smarter bunch in HN all been degraded in critical thinking dept. It's sad to see comments just taking it up as its without using it even once.