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

Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

research.meta.ai

Post reply on HN
Print view View original

341–350 of 682 posts

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#341

Post by dominotw »

andelink wrote: post #290
dominotw wrote: post #212

Earlier quoted context omitted.

There is a big astroturfing going on social media platforms by the chinese. Did you notice 'day in a life of unmarried 30 yr old lady in china' videos flooding usa social media. Regular ppl in the west now hold mildly positive views of the ccp and how 'advanced' china is than usa. Then there are europeans who now are looking for china to give them the technology handout now that relationship with usa has soured.

I only see those type of videos on 小红书

https://www.youtube.com/watch?v=PEpo4yCut2E

i thought youtube and instagram are blocked in china. how are these ppl posting these?

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#342

Post by skohan »

exe34 wrote: post #220
skohan wrote: post #134

Earlier quoted context omitted.

I've been coding using the LLM server in my living room for the past few weeks, and I haven't had this much fun with tech for ages

Can I ask, do you feel the pain of the level of abstraction? I haven't tried local in a few months, but last time I tried, I felt like I was directing a coding exercise - whereas with a frontier model, it feels more like directing a product building. "I need this feature", vs "write code to do this in this file".

> write code to do this in this file

I haven't had to micromanage to this level. I usually start with a spec for a feature, which will be as detailed as I am opinionated about the feature. But it's usually on the level of a high-level context, plus some key implementation details (technology choices, key requirements, maybe an interface/API specification to 80% detail), and then the project already has high-level policies documented about e.g. how to structure files within the project.

Then I do a planning phase, task breakdown, and implementation of subtasks all within the model. I do read through it, but mostly the quality is good and I might make a couple notes. Then I do a review phase, which usually picks up a couple things. I'm moving towards less manual review of results and more automation as I learn what I can and can't trust the model with.

There's definitely a capability gap vs. larger models, but honestly I kind of prefer this workflow, as I stay more in touch with how the codebase is structured.

And it's great to be able to experiment as much as I want without worrying about how many tokens I'm burning or how close I am to a usage limit.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#343

Post by nbardy »

mmaunder wrote: post #249

Remember when we needed 200 servers for an enterprise website because Apache used one process or thread per connection - and Nginx collapsed that into a single box overnight? That moment for LLMs is near. It’s going to move us from the big iron era of AI to small portable brains. Nature has already proved it’s possible with 20 watts and very little heat generation. And I think the data center buildout will end in car…

Everyone keeps repeating this who doesn’t understand the underlying technology.

Small llms are still way more efficiently server on big GPUs.

Sharing server capacity takes advantage of the massive parallel throughput and sharing of memory bandwidth.

You are sharing the GPUs with thousands of concurrent users.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#345

Post by dofm »

andy99 wrote: post #327

The gguf is up and works, I don’t know if it’s them or unsloth that’s facilitated this but it’s nice because e.g. Inkling still doesn’t appear to have support in llama.cpp which makes it irrelevant to a class of user. Unfortunately I don’t have enough experience with Qwen 27B to immediately compare, but I do it’s Qwen 3.6 35B A3. It’s much slower obviously but it seems to be way more efficient with its thinking to th…

I don't really use the Qwen 3.6 27B though I do test the variants (Bonsai, ThinkingCap).

I really like the 3.6 35B A3B for experiments, and it seems OK, but as you say, it spins round in thinking loops more than say the 26B Gemma 4 does. If Muse doesn't actually-wait itself as much it will be very interesting.

I am just downloading it to run my small tests.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#347

Post by logicchains »

seizethecheese wrote: post #319
ericmay wrote: post #171

Earlier quoted context omitted.

It’s rather amusing to me to read comments like this, and then simultaneously whenever a Chinese company or team releases open-weight models or whatever there is a giant round of applause, America is so behind, and there’s nothing but positive things to say about the intelligent, creative, and well-intentioned Chinese engineers (which is true, America certainly doesn’t have a monopoly on great people). Don’t you know…

While composing a reply to a comment throwing tons of shade on American AI, I took some time to check out the commenter’s HN profile. Their comment history was about 50% such comments. Their submission history started with an article about how Russia was unfairly blamed for some hacking campaign. It’s entirely possible that this is not a foreign influence campaign. Perhaps there’s a group here that is simply anti-Ame…

There's literally a Chinese-funded influence campaign against American AI: https://openai.com/index/disrupting-malicious-uses-of-ai-dat...

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#348

Post by Aurornis »

cmiles8 wrote: post #97

With the business model for API based LLMs looking iffy at best it seems like we’re heading back to the “server under your desk” era of IT again.

> at best it seems like we’re heading back to the “server under your desk” era of IT again

Maybe in the very long term. If companies go local, the efficient model is to buy some big hardware to share among developers.

I run local models. Even with 128GB unified memory systems or a 5090 or RTX 6000, the generation speeds X model quality X context length is still far behind what I get from my SOTA model subscriptions. I also pay a lot more for the locally generated tokens in electricity and hardware costs. I'm also limited in parallel requests to the local box. The list goes on.

I really like running local models, but for any given point in time it's more efficient to have a big central box aggregating requests and churning through them. So maybe companies buy $300K servers and try to split it among 30 users instead of trying to buy 30 x $10K boxes.

More likely, they rent time on cloud servers by the month so they can adapt the hardware when new models come out with new requirements.

Then some day in the distant future when hardware is cheap and plentiful again, it might make sense for us to go back to individual boxes under the desk.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#349

Post by logicchains »

christina97 wrote: post #320
ericmay wrote: post #171

Earlier quoted context omitted.

It’s rather amusing to me to read comments like this, and then simultaneously whenever a Chinese company or team releases open-weight models or whatever there is a giant round of applause, America is so behind, and there’s nothing but positive things to say about the intelligent, creative, and well-intentioned Chinese engineers (which is true, America certainly doesn’t have a monopoly on great people). Don’t you know…

The GP is claiming Meta is an awful company for what they have done and how they continue to treat their employees. That’s a perfectly ok opinion to hold, and many seem to agree. Have DeepSeek, Moonshot, or the other Chinese AI companies done such things that attract moral outrage?

Chinese tech companies make their employees work 16 hour days, 6 days per week, compared to them Meta are absolutely saints.

Re: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows

#350

Post by jkl5xx »

seizethecheese wrote: post #319
ericmay wrote: post #171

Earlier quoted context omitted.

It’s rather amusing to me to read comments like this, and then simultaneously whenever a Chinese company or team releases open-weight models or whatever there is a giant round of applause, America is so behind, and there’s nothing but positive things to say about the intelligent, creative, and well-intentioned Chinese engineers (which is true, America certainly doesn’t have a monopoly on great people). Don’t you know…

While composing a reply to a comment throwing tons of shade on American AI, I took some time to check out the commenter’s HN profile. Their comment history was about 50% such comments. Their submission history started with an article about how Russia was unfairly blamed for some hacking campaign. It’s entirely possible that this is not a foreign influence campaign. Perhaps there’s a group here that is simply anti-Ame…

Would be nice if there were a hn feature, userscript, or plugin to just filter comments from new accounts. Bonus if there was some sentiment analysis or llm-based analysis to filter out unsubstantiated inflammatory comments too.
Post reply on HN