Recent content by myzz

https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned TLDR or the takeaway from this is that LLMs do not function the way normal code does. Its much more opaque, non-deterministic, and at this point will "run" anything fed to it, hence prompt-injection and other techniques.

Credit Default Swaps where have I heard that before...

Not only the prompting but being able to tell if the output is complete garbage or not.

Good analogy actually - because when you do math with a calculator you have known inputs and expected outputs and it is deterministic. AI coding is none of those things. Not yet at least. The big issue is that (some, maybe most) software is made for others to use. Some who even pay. They expect...

A while back I spoke to someone studying cg animation at a university. The training started by doing traditional cel animations to get the basics of motion and keyframing etc. This is the only way going forward if we don't want things to collapse. Coding should be taught and in some cases even...

Didn't know where to put this post, but it started with wanting to test drive some smaller models before shelling out for my own hardware so I'll put it here... Stumbled on Qwen 3.8 27b being served on Cerebras hardware, and wow it is FAST. Got 500tk/s in my testing via a 3rd party reseller...

Same here! I got Claude to build scripts to export processed clips out of Resolve, so now looking into an agent to run it start to finish from the setup of the project and paramaters to a final folder of clips with effects like noise reduction, stabilization, etc. baked in.

I suppose this is a move to be like MS <-> Github? Except betting on the future - once every last corner of github is scraped its worthless and these LLMs are the future.

I like it, it makes sense (y) I thought maybe more separation from local vs. cloud models would be good but reading through the posts it works.

The most bizarre thread I have seen here to date. 🙃

You are correct, this setup seems to be the best bang for the buck right now if you want useful work. "Dev kit" or not. Prefill is what kills the performance on the mac. Also performance doesn't seem to scale well with multiple macs. I like the cut of your jib. To me this stuff started getting...

That is a pretty interesting option. $8208 over 3 years, for 256G + 4tb, similar specs to 2x Sparks.

google Acemagic spyware... credential stealers, malicious chrome extensions, some reports of the malware remaining after reinstalling windows... I'd definitely avoid this brand.

Natural language interface to web search was always a great and ethical use for LLMs. If it was all local and we could choose our model and web index to search then I'd have no complaints about AI. Zarathustra[H] thanks for sharing your process, I may do exactly the same as you (I have an EPYC...

I spent a LOT of time searching, but managed to find some decent deals on used RAM. Am running 16GB single stick only for the time being - my server board allows single stick luckily. Performance is fine for my use, which is 2-3 light users. Another option is DDR4... for a storage server you...