I miss when tech was exciting

It’s not hard _for you_.

Only tangentially related really but almost all of the variance I have ever observed in ability to remember things like this is just trying at all to use a mnemonic or routine.

The above routine is a specific practice to remember something — I basically think it would be effective for anyone that actually did it, and almost all non-adherence would be at step zero.

Looks cool! One bug I found:

`curl www.google.com` works using 8.7.1 on macOS, but I get "Please enter a valid curl command" on your website.

:) the curl command parser expects some flags of GET, POST, stupidly overlooked, will get it fixed!

Haskell: everything is a function

Genuine question: is farming a blue collar job? My (possibly incorrect) image of farming is management of heavily industrialized processes, not of rolling up your sleeves.

Careful study of farming often reveals that it's a mix of landowners (rich on paper, possible cashflow problems) and workers (usually immigrant, often undocumented, in which case they're not voting at all).

Fair point. I guess it is more like managing, say, a building or plumbing firm.

I guess what I should have said is "contempt for people outside of the laptop class" (and yes farmers may use laptops but you get what I mean).

Have you see any farmers with white collars? I haven't, they tend to wear working clothes even if they have lots of money.

Not trying to be snarky: why do you hate paying a regular fee for regularly updated software? Wouldn't the alternative be upgrade pricing, which is essentially just subscription pricing with extra steps?

Wow, I had no idea they even made 8k 120hz screens, that’s wild.

The Macintosh plus, released in 1986, cost $2600 at the time, or $7460 adjusted for inflation.

It even came with an official display! Nowadays that's a $1,600-$6,000 accessory, depending on whether you own a VESA mount.

I definitely prefer the 4.5, but that might just be because it sounds 'less like ChatGPT', ironically.

It just feels natural to me. The person knows the language but they are not trying to sound smart by using words that might have more impact "based on the words dictionary definition"

GPT 4.5 does feel like it is a step forward in producing natural language, and if they use it to provide reinforcement learning, this might have significant impact in the future smaller models.

Feature request: I would like to know if I can run _any_ LLms on my machine, and if so, which.

I've now had multiple people ask for this - I will work on adding a new tab for this feature as it is a little different than what the site was originally intended to do.

Generally speaking models seem to be bucketed by param count (3b, 7b, 8b, 14b, 34b, 70b) so for a given VRAM bucket you will end up being able to run 1000's of models - so is it valuable to show 1000s of models?

My bet is "No" - and what really is valuable is like the top 50 trending models on HuggingFace that would fit in your VRAM bucket. So I will try build that.

Would love your thoughts on that though - does that sound like a good idea?

I see your point. I think the solution you mention (top 50 trending models) is as good a solution as I could come up with. Maybe the flow should be: Select a GPU / device -> list all the runnable models, sorted by popularity descending. How you want to operationalize popularity is another question...