syntaxing

How much VRAM does parakeet take for you? For some reason it takes 4GB+ for me using the onyx version even though it’s 600M parameters

Isn’t this the motivation behind polymarket? To incentivize those that have information to bet as a signal of “truth”. What I don’t get is why would anyone bet on this stuff that don’t have insider information besides those with gambling addiction.

It doesn’t though. If you think about it, improper English and slang strongly effects cultural and social bonding. I too would feel the opposite party is pretentious if someone is correcting me for a casual conversation. If it’s a professional relationship, that’s different.

Can you blame them? You have 10 million people give or take in about 50 miles.

OpenAI have been very generous in their plans in terms of token and what you use it with. Is Codex better or as good as Opus for coding? No. Is it a decent alternative? Very.

I once went to go pick up takeout and they covered the no tip button with a sticker. I was so confused so I put in 10 cents because I could find the button at first. I stopped going to the place since.

Pushing Dan Ammann out was a bad idea. I personally like the original set up at the time. Kyle as the CTO and Dan as the CEO. Kyle was great as an internal CEO, he was calling most of the internal shots anyway. The accident would have played out very differently if Dan Ammann was the CEO IMO.

(Also former Cruise employee)

Why a Twitter post and not the official Google blog post… https://blog.google/innovation-and-ai/models-and-research/ge...

Wow that was a fun read, I never thought about the technical implementation of these verification systems.

Was more mentioning the article about the economic aspect of China vs US in terms of AI.

While I do understand your sentiment, it might be worth noting the author is the author of bitandbytes. Which is one of the first library with quantization methods built in and was(?) one of the most used inference engines. I’m pretty sure transformers from HF still uses this as the Python to CUDA framework

Tim Dettmers had an interesting take on this [1]. Fundamentally, the philosophy is different.

>China’s philosophy is different. They believe model capabilities do not matter as much as application. What matters is how you use AI.

https://timdettmers.com/2025/12/10/why-agi-will-not-happen/

Scale. You can monetize on the people that don’t pay the $200/month. Obviously I have nothing to prove this statement, but I wouldn’t be surprised if the subscriptions are loss leaders.

Not OP but I doubt it. I’m in my mid 30s and when I grew up there in the 90s, Suffolk county was bumble. Some people had horses on their land. After 9/11, a ton of people moved in from the city and the population absolutely ballooned. Over two decades, the population grew so much that just Nassau county and Suffolk county combined has more people than a handful of states. People come and go too (including myself) so unless some organization is tracking us, it’ll be hard to pinpoint.

Aha likewise, I swear, between the ticks and the polluted water, a good amount of us are screwed. Grumman has put some nasty stuff into the ground too. I remember growing up how they mentioned it was slowly seeping into the aquifer. Took me ages to convince my parents to get a RO machine

I worked at BNL during college days through the SULI program! Some of my peers from college is working there full time now too. I got to work on some really cool stuff but unfortunately a lot of the tenured researcher I knew have seem to left. I heard a lot of researchers left during Trump’s first term.

I know there’s metal plates you can self stamp for crypto wallets. I’m sure you can do the same for this purpose.

First time hearing the term micro bakery. Is there an equivalent for restaurants? Like a micro restaurant? Seems like a fun idea for my retired parents.

As a MechE turned SWE, always a fun read when SWE try hardware.

> Blink and you’ll get a different measurement.

This means your environment is not controlled enough. Also quality control is usually done in terms of statistics. You might want to read something called gauge R&R. That being said, you should be proud of being able to ship a physical product!

As for quality checks, software quality teams pales in comparison to hardware quality teams. Mainly as you said, there’s a lot checks you can do in software. For hardware, bigger companies have to have their vendors qualified. The vendors have to follow their customer guidelines and do outgoing inspection. Then the company has a division to do incoming inspection. There’s a traveler that follows the kit (of parts) and there’s usually subassembly quality checks. Then final full build checks before it leaves the door.

Is Qwen next architecture ironed out in llama cpp?

Kinda sucks how it seems like there’s no CI that runs on hardware.

I don’t think so. You can see the issue ticket linked in the PR. Whether that issue ticket is related to the blog post is unknown https://github.com/ml-explore/mlx-swift-examples/issues/462

With the adoption of sodium batteries, I wouldn’t be surprised if solar panel + sodium battery would outperform this system by a lot.

To a certain extent, yes. The reason why the water is there is because the thermal flux of the ground is low, so the large mass of water provides a strong buffer. But you can’t cheap physics. You would need a crap ton of salt hydrate to accommodate a whole season of heat needs, even if you don’t factor in thermal loss from the container.

So…geothermal? I wish this was possible too but I don’t see how it will work scientifically. Water is one of the chemicals that have one of the highest thermal mass/specific heat (maybe 1/3 of salt hydrates). Even then, you have to bury a crapton of water underground. This design mentioned in the article is more for short term, like 12 hours storage (since they’re accommodating for solar in nighttime)

Interesting model! Seems to underperform GLM 4.7 Flash though (according to benchmarks)

Unfortunately it’ll be a lot harder for CAD because of all of the other lock in like PLM/ERP integration. A good PLM is half the product. I know a good amount of companies that do not use solidworks because their PLM is absolutely crappy (but I haven’t been a MechE for a couple years now so things could have changed)

It’s actually really easy to use mitmproxy as a…proxy. You set it up as a SOCKS proxy (or whatever) and point your network or browser to the proxy. I did this recently when a python tool was too aggressive on crawling the web and the server would reject me. Forced my session to limit 5 requests per second and it worked rather than finding the exact file to change in the library. Just do the same to your browser and then turn on the capture mode and you’ll see the requests

Nile red made a fun video about the original prototype (transparent wood)!

So refreshing to see open source models like this come from the US. I would love for a 100Bish size one that can compete against OSS-120B and GLM air 4.5

I’m really excited for lmster and to try it out. It’s essentially what I want from ollama. Ollama has deviated so much from their original core principles. Ollama has been broken and slow to update model support. There’s this “vendor sync” I’ve been waiting (essentially update ggml) for weeks.