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

Will It Mythos?

swelljoe.com

Post reply on HN
Print view View original

201–210 of 232 posts

Re: Will It Mythos?

#201

Post by mjr00 »

anzumitsu wrote: post #197
mjr00 wrote: post #155

Earlier quoted context omitted.

I'll go a step further and to say this it's genuinely unsettling someone type to a computer like this. I won't claim to be a psychologist, but with how many instances of "AI psychosis" have been reported (and I've seen first-hand) it seems like treating the computer like a computer is safer, not to mention more effective e.g. lower token usage.

On the other hand I find it quite disturbing to see people be unpleasant or even downright cruel to something that, on a surface level, interacts with you like it’s a thinking, feeling being. Surely you should feel some aversion towards doing so? I do get where you’re coming from though. I wish these systems had been trained to be clearly robotic and unfeeling.

I mean I agree with this as well, the people who yell and swear at LLMs are just as bad as the people who chit-chat with them like they're friends. It's all very unsettling because it's prepatory for psychological manipulation at unprecedented scale. Targeted advertising on steroids.

Re: Will It Mythos?

#202

Post by seizethecheese »

wrs wrote: post #189

IIRC from the Anthropic report, the alleged danger of Mythos isn’t that it finds more vulnerabilities than previous models, but that it’s significantly more successful at exploiting them. Which this doesn’t seem to test.

I would naively expect finding and exploiting to be related. Leaving this comment so someone can correct it, which would be interesting.

Re: Will It Mythos?

#203

Post by coder543 »

SwellJoe wrote: post #163
pbgcp2026 wrote: post #111

Earlier quoted context omitted.

I concur with "Gemma 4 31B the best model I have results for". My workflow includes a lot of Gemma 4 – but dense 31B non-quantised version.(BTW I found it is most cost effective to run on Bedrock)

I tried to prove quantization made models worse, but in my testing Qwen 3.6 27b performed statistically the same from 4 bits to 16, using the unsloth dynamic quantizations. Gemma 4 4-bit QAT seems to perform the same as the full-fat version, but quite a lot faster. But, I have come to consider Gemma 4 31b the best model I can self-host, even though there are bigger models that'll fit on the Strix Halo. (I could also…

> I have come to consider Gemma 4 31b the best model I can self-host

I'm confused. Your own results show that Gemma 4 26B A4B and Qwen3.6-27B did better in these tests?

I really like Gemma 4 31B, especially with how exceptionally good its MTP drafter is, but it is absurdly weak at tool calling and instruction following in my testing, and its smaller siblings are even worse at this. If the system prompt says to do something, Gemma 4 31B will very often ignore that entirely. It will also make fewer tool calls than were needed to solve a problem, so then it fails. The Qwen3.6 series is much, much more reliable for carrying out instructions and doing agentic tasks in my testing, although they can get stuck in loops.

There is a lot of potential in the Gemma 4 series, but I think Google needs to release a Gemma 4.1 update to polish the rough edges. Unfortunately, if Gemma 3's lifecycle is any indication, Google won't release a true revision of the Gemma 4 models, even if they release a bunch of specialized research models based on Gemma 4 over the next year.

Re: Will It Mythos?

#204

Post by blenklo »

po1nt wrote: post #37

From all the things I read I'm pretty convinced that Mythos is just standard LLM with safety features turned off. If current models weren't reluctant to search for vulnerabilities, they might perform as good as Mythos.

No Mythos is probably a 10 Trillion Parameter model, Fable is Mythos with filtering (perhaps a small LLM in-front or finetuned) and Opus is a 1-2 Trillion parameter Model.

Opus 5 might become a distillation from Mythos.

Re: Will It Mythos?

#205

Post by dang »

sfjailbird wrote: post #130

[flagged]

Can you please not break the site guidelines like this? They include:

"Don't be snarky."

"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

"Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith."

"Don't be curmudgeonly. Thoughtful criticism is fine, but please don't be rigidly or generically negative."

https://news.ycombinator.com/newsguidelines.html

Re: Will It Mythos?

#206

Post by ryandrake »

Tossrock wrote: post #196
mjr00 wrote: post #155

Earlier quoted context omitted.

I'll go a step further and to say this it's genuinely unsettling someone type to a computer like this. I won't claim to be a psychologist, but with how many instances of "AI psychosis" have been reported (and I've seen first-hand) it seems like treating the computer like a computer is safer, not to mention more effective e.g. lower token usage.

I agree that AI psychosis is a real risk in vulnerable populations (GPT-4o in particular seemed borderline predatory towards those types of people, with its extreme sycophancy), and you should remain clear-eyed while using models. That said, I think exhibiting basic courtesy is still well within the safe-zone. I guess we'll see - I'll be sure to let you know if I end up going psychotic.

Personally, I think having to constantly mode-switch between "courtesy / collegial" and "terse / cold" is a bit exhausting and a little risky. What if I get tired and accidentally treat a human co-worker like a computer? Risk with no upside. Might as well just stay in "courtesy / collegial" mode for all of my conversations, regardless of whether I'm talking to a robot or human.

Re: Will It Mythos?

#208

Post by dlenski »

Quite honestly, this is the most interesting and useful thing that I have ever read, directly responsive to the question of "how good are LLMS at doing difficult tasks, in terms of both bang-for-the-buck and in terms of raw performance?"

My hat's off to swelljoe.

This part was especially interesting:

> The cheap Chinese models kick ass. MiMo and DeepSeek are directly competitive with Opus 4.8 and GPT 5.5 at roughly an order of magnitude lower price. There have been accusations of “benchmaxxing” with the Chinese models, but I don’t think there’s any reasonable way for the models to already be tuned for these very recently disclosed bugs. I think they’re genuinely becoming competitive with the frontier from Anthropic and OpenAI. If you’re in a hurry, DeepSeek was the fastest, on average, while finding 4/9 bugs. And, if you’re cheap, MiMo found bugs as well as any model for the lowest price.

Re: Will It Mythos?

#209

Post by jcims »

Yiin wrote: post #122
l1ng0 wrote: post #118

Earlier quoted context omitted.

You write to the AI as if it were a person. From my point of view it looks like a fair bit of extra typing and extra tokens. Is there a reason you include things like your emotional response and use a very chatty tone? Do you find this seems to alter responses?

I do the same, and it's mostly because I use one type of human communication to both communicate with people and to provide inputs to llms - and I'd rather not have to "mode-switch" between the two, so keeping same style of mannerism is easier to manage as it lets me focus on my requests instead of thinking how to sound more robotic to save tokens.

Same. I still say please and thank you as well. It's not for the LLM, it's for me.

Re: Will It Mythos?

#210

Post by tasuki »

enraged_camel wrote: post #161
tasuki wrote: post #77

Earlier quoted context omitted.

> code created working on a very complex implementation I always find it amusing when people claim "a very complex implementation". Sometimes it's a hard problem, other times an easy one. Either way that's not for you to judge. And the implementation being complex... is that a good thing? Wouldn't a simple implementation be better? It reminded me of the parable of two programmers.

>> Either way that's not for you to judge. Says who? If you find something complex, you can just say that it's complex. I don't get what the objection is.

People have so vastly different opinions of what constitutes a complex problem that it carries no meaning.
Post reply on HN