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

211–220 of 678 posts

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

#211

Post by esafak »

fwipsy wrote: post #192
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…

Good points, I personally believe that if/when China takes the lead, they will immediately stop releasing model weights. It only makes sense as a strategy to counterbalance (current) American labs' monopoly on frontier models. Holding both those positions would be hypocritical all right, but are you sure it's the same people commenting/voting in both cases? I don't think there's a strong consensus on Hacker News. Eve…

Free models help move robots; a complement. I can foresee the models staying free.

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

#212

Post by dominotw »

ericmay wrote: post #171
avaer wrote: post #101

I lament the comments saying this in any way redeems Meta (the company). The researchers releasing this stuff have almost nothing to do with Meta other than being bankrolled by the slaughterhouse. You aren't the customer, you are the pawn in big tech's game of thrones. Your good will is a commodity to be traded, almost literally. It will be used against you the moment it's convenient. This is open weights because Met…

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…

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.

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

#213

Post by bko »

monster_truck wrote: post #119
avaer wrote: post #101

I lament the comments saying this in any way redeems Meta (the company). The researchers releasing this stuff have almost nothing to do with Meta other than being bankrolled by the slaughterhouse. You aren't the customer, you are the pawn in big tech's game of thrones. Your good will is a commodity to be traded, almost literally. It will be used against you the moment it's convenient. This is open weights because Met…

Meta can never be redeemed, but it's still valid to admit that FB at one point had a very badass engineering culture. They're one of 2 companies I would absolutely never work for (weapons etc aside). FB's recruiters hounded me so often I requested that they blackball me. The day they became Meta, I learned this by checking my email to see that they started trying to reach out again. I once again requested that they b…

Meta doesn't need to be "redeemed". They have two of the most popular social media apps in the world. And theyll prob survive without ever having you work there

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

#214

Post by wolttam »

staplor wrote: post #205
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.

What do you mean iffy? The major AI labs are gross profitable when selling access to inference. In addition, the best models have trillions of parameters and are most efficiently served on large, expensive clusters and served to many concurrent users.

They make money on each token when you look at the electricity and interconnect fees, but no, I don’t think they’ve turned a profit on their Capex, even a little bit

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

#215

Post by energy123 »

fwipsy wrote: post #192
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…

Good points, I personally believe that if/when China takes the lead, they will immediately stop releasing model weights. It only makes sense as a strategy to counterbalance (current) American labs' monopoly on frontier models. Holding both those positions would be hypocritical all right, but are you sure it's the same people commenting/voting in both cases? I don't think there's a strong consensus on Hacker News. Eve…

I see it as a strategy to increase capital costs for American frontier labs. By eroding the expected ROI of frontier labs, you deter private investment into them, which slows OpenAI and Anthropic in particular, giving space for the laggards to catch up.

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

#216

Post by ComputerGuru »

sajithdilshan wrote: post #10

Still needs 32-64GB memory to run it locally. 64GB Macbook pro with an M5 chip costs more than 4k Euros in Germany. A more practical model would be a language specific (e.g Python or JVM language) and excellent at tool calling and reasoning. Maybe that way they can shrink it even more.

There is no good reason to believe language-specific models are going to be any meaningfully smaller, just worse. Same as English-only models vs those trained on a multilingual corpus.

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

#217

Post by gdhkgdhkvff »

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.

Why do you say API based llms looking iffy at best? Do you just mean current profitability due to market pressures from some companies’ subsidized investor money?

Surely, even if you’re just using open weights models, it should theoretically be cheaper to use them in a highly optimized cloud architecture(even with vendor markups) rather than each person serving their own models from much less efficient (and more importantly, much less consistent volume) self-owned “server under your desk”?

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

#218

Post by nickludlam »

dannyw wrote: post #168
ignoramous wrote: post #48

Earlier quoted context omitted.

> Meta did not abandon opensource Open weights* I don't think outside of the Big 3 (Ant, OAI, GDM), given the strong competition from China, any other Lab has a chance at capturing the coding market if they aren't open weights (save for xAI whose latest Grok looks every bit good & will probably rely on Cursor for distribution instead of going open weights). There's literally no other selling point, as the capabilitie…

Don’t sleep on NVIDIA and Nemotron. It’s not completely open source, but they actually release their pretraining and post-training datasets with some redactions for (cough) pirated content. They also have very good code and playbooks for actually doing a fine-tune, CPT, etc. Even if you’re not tuning a Nemotron model, its mixes are very excellent for your replay data slice; or general experiments. Way better curation…

Yes, I second Nemotron. I'm using Ultra remotely and Super locally, and I find them very useful for RAG-like problems. I wouldn't really use them for coding.

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

#219

Post by danielEM »

dannyw wrote: post #96
Gecko4072 wrote: post #19

Earlier quoted context omitted.

You personally? Just curious. Context window is also a factor and ram isn’t really cheap. Sparks are assembled units which I like.

For the same price as a DGX Spark here (A$8499) I can buy roughly 544GB of DDR5-5200MHz from retail; which on a quad channel platform would deliver ~160gb/s real world; and ~320gb/s with octa channels (Xeon, Threadripper Pro). If you can afford it or somehow find a used unit, you can go Epyc for 12 channels. 8/12 channel DDR5 will beat DGX Spark in inference/decode even without a GPU of any kind, as it’s memory bandw…

Been investigating these multichannel AMD based platforms last year and seem like none of them can in real scenarios utilize anywhere close to their theoretical bandwidth.

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

#220

Post by exe34 »

skohan wrote: post #134
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.

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".
Post reply on HN