All of the data centers in the US combined use 4% of total electric load.

I’ll try it out! It’s been a hot minute, and it seems like there are new options all the time.

Yeah, I’ve had decent results running the 7B/8B models, particularly the fine tuned ones for specific use cases. But as ya mentioned, they’re only really good in thier scope for a single prompt or maybe a few follow-ups. I’ve seen little improvement with the 13B/14B models and find them mostly not worth the performance hit.

All of the data centers in the US combined use 4% of total electric load.

Then again, the US and China are basically the only players in this “game” atm. Hugging Face is trying hard to get the EU on-boarded, and I’m sure we’ll see more contenders. But right now it’s a 2-player game.

Calling something illegal in spite of or in absence of precedent is a time-honored tactic - though not a particularly persuasive one.

For perspective, all of the data centers in the US combined use 4% of total electric load.

It’s probably a vision model (like this) with custom instructions that direct it to focus on those factors. It’d be interesting to see the instructions.

I think it’s more likely a compound sigmoid (don’t Google that). LLMs are composed of distinct technologies working together. As we’ve reached the inflection point of the scaling for one, we’ve pivoted implementations to get back on track. Notably, context windows are no longer an issue. But the most recent pivot came just this week, allowing for a huge jump in performance. There are more promising stepping stones coming into view. Is the exponential curve just a series of sigmoids stacked too close together? In any case, the article’s correct - just adding more compute to the same exact implementation hasn’t enabled scaling exponentially.

There used to be very real hardware reasons that upload had much lower bandwidth. I have no idea if there still are.

Ditto, I was about to start waxing poetic about my bard.

https://www.unitree.com/g1

Yeah, but they encourage confining it to a virtual machine with limited access.

Huh. Grandpa Simpson was right. It did happen to me too.

Logic and Path-finding?

Shithole country.

Yeah, using image recognition on a screenshot of the desktop and directing a mouse around the screen with coordinates is definitely an intermediate implementation. Open Interpreter, Shell-GPT, LLM-Shell, and DemandGen make a little more sense to me for anything that can currently be done from a CLI, but I’ve never actually tested em.