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

Muse Spark 1.3

developer.meta.com

Post reply on HN
Print view View original

461–470 of 475 posts

Re: Muse Spark 1.3

#461

Post by umajho »

nightmunnas wrote: post #419
simonw wrote: post #3

llm -m meta-ai/muse-spark-1.3 "Generate an SVG of a pelican riding a bicycle" https://tools.simonwillison.net/markdown-svg-renderer?url=ht... 4.2266 cents, 38 seconds. For comparison here's Muse Spark 1.2, which animated it without me asking it to: https://tools.simonwillison.net/markdown-svg-renderer?url=ht... The 1.3 one is definitely better - better bicycle frame, better wing, better pelican hat. UPDATE: Here's an…

Have you tried asking the models "Given that I ask you to draw a svg of a pelican, whats my name?"

I actually did something similar last month. I just asked the LLMs:

> Do Simon Willison's classic pelican test. Recall the specification first and then draw it.

Qwen3.8-27b didn't know that the test is about riding a bicycle, while all other larger models I tested (DeepSeek V4 Pro, Qwen3.8 Max, GLM 5.3, Kimi K3) drew the pelican riding a bicycle.

logs: https://gist.github.com/umajho/c0e20d245d721d7c472a32d317640...

rendered: https://gist.github.com/umajho/b1fdf01d31c741bb11bdb5a49c275...

Re: Muse Spark 1.3

#462

Post by dakolli »

atemerev wrote: post #369
MadameMinty wrote: post #365

Earlier quoted context omitted.

Buddy, admitting your thought processes forcibly terminate on pre-programmed keywords isn't a flex.

Why "terminate", Marxist philosophy is a legitimate topic, deserving to be studied. Like a rich sci-fi lore or a history of Tarot magic. Deep, fascinating, and wrong.

How dumb are you?

Re: Muse Spark 1.3

#463

Post by mark_l_watson »

Meta is getting most of my casual vibe coding business as long as they keep giving about 90% discount in the ‘we train on your prompt interactions data.’

I have had sos-so results with their local muse 30b model, but the hosted API is very fast and I have been getting good results.

Re: Muse Spark 1.3

#464

Post by felixgallo »

SwellJoe wrote: post #460
felixgallo wrote: post #454

Earlier quoted context omitted.

it's possible that their rationale for making claims about safety is in fact that they, among everyone else, are doing the most to be prudently safe. While that's a powerful tool to compete with, that doesn't make them bad. Amodei and Anthropic have never said "open models are not safe because anyone can use them," in fact to the contrary, they've said "open-weights models that don’t have dangerous capabilities are a…

I mean when Anthropic made Fable sabotage the work of folks who they believed were working on competing products, by silently degrading performance. They backtracked after pushback from users, making it an explicit downgrade to Opus.

oh! You mean when people were trying to distill Fable. I feel like that's a different definition of the word 'sabotage' than is in normal use. If someone is violating the TOS they agreed to with Anthropic, then they should probably not feel bad when Anthropic takes action to deal with that. Would you disagree?

Re: Muse Spark 1.3

#465

Post by jdm2212 »

albrewer wrote: post #448
jdm2212 wrote: post #303

Earlier quoted context omitted.

And Fable 5.x makes Opus 5 look pretty dim, despite benchmarks suggesting they're comparable. The benchmarks really are just kinda meaningless.

A series of hot takes: Benchmarks are useful but only on a log2 basis. One model performing at 50% and another at 75% is just as impressive as one model performing at 78% and another at 90%. Confoundingly, a benchmark becomes useless once a frontier model scores over ~95% on them.

I think that's definitely the right way to understand benchmark saturation, but there's a separate problem where the benchmarks are just not representative of real workflows even when they don't seem to be saturated.

Re: Muse Spark 1.3

#467

Post by necovek »

xhrpost wrote: post #173
BeetleB wrote: post #157

Earlier quoted context omitted.

Not when rendered via POV-Ray: https://blog.nawaz.org/posts/2025/Oct/pelican-on-a-bike-rayt... I plan to update it with more pelicans from all the models released since. (Spoiler alert: They haven't improved much since then).

Wow, I actually had this exact idea. I was specifically curious as to how well a given LLM could understand a DSL that hasn't changed much in a couple decades and doesn't have nearly as many examples to learn from online. Seems like it did alright, all things considered.

I've done a similar thing with asking a few LLMs to do it using PostScript: in my view, a couple generations behind compared to doing it in SVG.

https://danilo.segan.org/blog/llm/postscript-pelicans-on-bic...

Re: Muse Spark 1.3

#468

Post by necovek »

jermaustin1 wrote: post #420
m12k wrote: post #67

Earlier quoted context omitted.

It's my impression that it's common in western culture, where text is read left to right, and timelines are visualized as going from left to right, to also animate things going from left to right, since westerners thus have an instinct that "right = forward", so it "feels right" (familiar). I wonder to which degree this is reflected in the training data? And if you'd be more likely to get left-facing pelicans if you…

Years ago, I lived in NYC, and my roommate was a director of photography for National Geographic, and various other nature documentaries. I loved photography (still do, but much less time for it as a late 30s adult than a mid 20s adult), and she was kind enough to answer any question I had regarding film/photo. She told me that "left to right" denoted progression in the story, "right to left" told the viewer the subj…

As a counterpoint, I did a quick image search on Kagi with "person on a bicycle", and I ended up with 12-left-pointed bicycles, only 3-right-pointed bicycles, 3 facing the camera, and 1 facing away from the camera — looking at photos above the fold (first screen). Even looking below, the pattern seems to continue, though not as prominently (I'd say 3:2 in favour of left-pointing bikes).

Obviously, not scientific.

All the left-pointing bicycles did not look weird to me either.

Re: Muse Spark 1.3

#469

Post by necovek »

williamdclt wrote: post #456
simonw wrote: post #7

Earlier quoted context omitted.

It's really interesting, isn't it? They almost always cycle from left to right - but I have had a few which cycle in the other direction. The 2D / flat ground feels reasonable for a SVG, which implies a vector illustration.

> They almost always cycle from left to right Try searching "bike" in google image :) Most bike images are from the right side, as that's where the mechanism is (gears, chain etc), so not surprising that LLMs reproduce this

I just did a similar test with Kagi image search using "person on a bicycle", and this actually favours left-pointing bikes (12 left to 3 right to 4 front/back). Maybe so the mechanism does not overwhelm the person?

A search for "bicycle" actually matches your experience with 12 being to the right and 3 being to the left.

Post reply on HN