YHK - yet another hacker news clone

Our Smallest, Most Efficient Model: Muse Ember

31 points dvaplima 52 minutes ago 14 comments

simonw 22 minutes ago | parent

Six effort levels (minimal, low, medium, high, xhigh, max), so here are six pelicans (actually five, "high" didn't return a complete SVG):

https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

There's usually a reasonably strong correlation between thinking level and visual quality of the pelican. This is the first time I've seen that correlation appear to break - more reasoning tokens doesn't seem to produce an obviously better SVG.

meric_ 11 minutes ago | parent

Wow, minimal seems to be the best here interestingly. Only 10 reasoning tokens so basically none?

sjacob 10 minutes ago | parent

Incredible. How do you get these out so fast?

permalac 10 minutes ago | parent

Is there a problem if I like the minimal more than the others?

imimayj1337 9 minutes ago | parent

It does pretty insane to me that only on max setting (and after waiting 27 seconds) did you actually manage to receive an SVG where the pelican's legs are straddling the bike correctly.

open-paren 11 minutes ago | parent

I believe this is what the “crouton alpha” stealth model was

https://openrouter.ai/stealth/crouton-alpha

Starlevel004 10 minutes ago | parent

Luna 6 is getting a bit long in the teeth now. It's two full months old, but it was only a slight step above Luna 5.6, which was already four months old (Imagine saying this about anything else). So I'm not too surprised that a newer small model is beating it handily. I've been hoping for Luna 6.1/2 as the next model release for a few days now.

esafak 3 minutes ago | parent

Uniquely among models I've tried, Luna 6 is infuriatingly lazy. As if it expects me to do the work, unaware that it is a tool.

caaqil 8 minutes ago | parent

I'm always a bit surprised to see Meta talking about models. They have become (almost*) entirely irrelevant to the LLM race, which is weird because their AI lab used to be decent before LLM was cool.

What happened to zuck? Was the metaverse this destructive?

(*) Feeling charitable today

esafak 6 minutes ago | parent

They have started to catch up; the Spark series is good.

achandra03 4 minutes ago | parent

Isn't Muse Wonder at or at least very close to the frontier? Considering they essentially started from scratch after rebooting their AI efforts post-Llama 4 about a year ago it's pretty solid progress.

StarlessHours 3 minutes ago | parent

Meta is trying to stay relevant. They fell behind after llama 4, hired new talent and re-organized.

dom96 4 minutes ago | parent

Super frustrating that I still can’t give Muse Wonder Full a spin.

gopalv 3 minutes ago | parent

Model refusals should be a -ve score, not zero?

Treating the refusal as a 0 score erases the difference between lack of capability and a lack of willingness to perform.