Viewing profile — storus

Is there any cheap way to run personal websites without getting cooked by bots these days, degrading the performance? A $5/month VPS won't cut it anymore.

Many of those require a paradigm shift in our understanding of Universe, so I am not sure they are achievable with any convex combination of existing knowledge. We'd need some shar…

2x DGX Spark runs DeepSeek V4 Flash 0731 quite well and I already reimplemented a few classical games with it in a few hours in OpenCode with minimal hand-holding. I am expecting t…

I am wondering when will harnesses generate their own RLHF/DPO training sets and just LoRA finetune the models they are running?

[flagged]

Reference-to-video mode seems like all that was missing to enable completely independent cinematography as right now one couldn't stitch different scenes together properly without …

I think the window for a ban of open weight models is closing fast so let's hope US administration is going to miss it and we get Fable-level models (at least in some aspects) with…

As long as economics incentivizes next quarter thinking nothing will be done. We can't even handle human portion of global warming which is arguably more important than just some A…

There is probably some correlation between one's profession and fetishes. We already know some programming languages attract certain types of personalities/attitudes so why would t…

Sideloading also means installing an app you don't want to publish on any marketplace (for your own or family/friends use). Is there a better word for it?

This is nice, but Apple essentially blocks sideloading (outside test flight environment) and Google is moving there as well. While it has never been easier to produce individualize…

AI = cognitive automation?

Only theory that is a convex combination of existing theory. Any paradigm shift is currently unreachable to LLMs and can be only obtained by luck with RL due to the curse of dimens…

I hope they somewhat fixed the hallucination and forgetting plagued V4 previews and that it wasn't just benchmaxxed but the numbers hold in reality. Then it would be my choice for …

What really helped me was to run any .md/prompts through an LLM to find contradictions, duplicates or ambiguities, repeatedly. That led to agents much better following instructions…

There was a presentation at CS 25 Transformers United about some phenomena like chain-of-thought emerging only after training LLMs with at least 1T tokens and only in LLMs of certa…

The speech he had at congress didn't sound very flattering towards the beginning of his today's statement: https://www.youtube.com/watch?v=_i91NSOyxHM He didn't mention outright ba…

If your brain has a local metabolic failure leading to the inability to replete neurotransmitters, how taking a walk is a solution to your problem? You need to improve energetics f…

This feels like Nvidia's strategy doesn't really care about the few companies they invested to pushing frontier AI, but about scaling up the amount of GPUs/datacenters needed; open…

Aren't depressions coming with side-effects like inability to do anything at all? The block is somewhere else to overcome before even thinking about exercise and the brain might ha…

What would be the current best method to fine-tune it for my own specific agentic tasks? LoRA + DPO? GRPO? Something else?

Getting 404 on the OP's link. Does it mean it got banned or self-censored in the meantime?

It's not really Markov chain as you need full P(x_t|x_{t-1}, x_{t-2}... x_1) instead of just P(x_t|x_{t-1}).