Viewing profile — gunalx

Low quality ai slop it feels like.

Isn't us-east-1 also an early rollout region for new stuff as well?

We do know about the hardware needed for a given token speed. What that hardware costs, and electricity prices. With that its easy calculations to get about the profit margins for …

How dare they claim to buy stuff to boost their standing while actually just faking the entire thing.

Weigths directly in silicon is a bad idea with the way the space is pacing. Just look at chatjimmy.ai it is fast, but on the once good llama3.1-8b but now pretty useless.

Your tokens should defiently have expiry times on the range that you would need to login again.

5.1 going insane was probably also a inference quirk. Because it sometimes remained coherent the entire 200k context length.

3.5 9B can do thinking. Its just disabled by default in its gguf chat template.

The qwen models really seem to have this as a failure mode, its so annoying having a proper trace ending up in !!!!!! Garbage.

I find a llm in a harnes combined with manual ripgrep exploration is really effective of getting codebases. But you font always want to find what you find.

Interresting, Have you done any Møre testing trying to trigger this behaviour? If it is semi konsistent or even just alone it makes a god case to switch.

No word on pricing or inference options i could see so not that interresting if it is not available to test.

Pragmatically the difference does not really matter, om the other hand a executive order migth have more action behind it than a law.

Amazing. Next is automating this, automatically or manually gathering all domains they have registered, and spinning up Claude to register a similar domain and creating the counter…

Just because a measure is less useful doesn't mean it is useless. There is always a compromise between convince and security and in this case one would have to do even more screeni…

This feels like a weird combo of slop and a decent intro to llms, jargon.

Probable seconds per frame at least.

Google knows they will happen and even ships it with chrome.

The rugpull with the pricing change without further notice was not taken kindly by enterprice.

Its nice if you used local, but needed å beefier modell, or more context Window. It will eat input tokens, but you do that all the time unless you have input caching.

Definetly dont. Maybe Ås å fuzzy search to find information, or a summarizer, but else the temptation to skip the actual learning is yo high.

Utterly unreadable on mobile

We'll see. The qwen team has always released a few close to sota but proprietary models in between tgeir open releases. We did get 3.6 35B and 27B so its not all set in stone yet. …

But noe you van only afford the rock bortom low-end device.

aurora store isan option.