Maybe attention isn't all we need.

So “gpt2” seems to be coming from OpenAI lol. They should probably not return exact errors from providers

At least it's confirmed that no, it's not a 'Large Action Model' - it's an LLM.. lol

Haven't been much excited by wearable tech lately. This one looks cool though.

I just want to dev with my own models and control that screen. From what I can tell, that's actually what's available here.

Waiting for them to figure out a prescription solution.

brushed up my personal site and brain dumped a post on 🎶musicgen-songstarter-v0.2🎶

It covers:
- 🧠my thought process/motivation behind it
- ✏️notes on my previous experiments over the last 9 months
- 👀 training deets, Weights & Biases logs w/ hparams

nateraw.com/posts/training…

Okay, first pass over KAN: Kolmogorov–Arnold Networks, it looks very interesting!

Interpretability of KAN model:
May be considered mostly as a safety issue these days, but it can also be used as a form of interaction between the user and a model, as this paper argues and I…

wake up new neural network just dropped (holy shit)

Must be another one of those toxicity checks.

Careful.

One hit of baking sourdough and before you know it you're clearing plots.

I have found gpt2-chatbot to so far be exceptional.

If you've not tried it, you can for free at chat.lmsys.org then go to the direct chat tab or arena and choose gpt2-chatbot.

Looking forward to learning more about this one.

I'm just sayin.

They disappeared the same day

Stuck in a local minima

dang wizardlm 8x22B still going thru a toxicity check huh

Sometimes I'm reading a research paper and can't help but wonder if the true intent of some method is to bait researchers into a deep rabbit hole to slow them down and waste time.

Another fine day for advancing Open Source AI whether some Delta exec likes it or not.

sorry Logan

Someone better explain to management that the whole 'Devin' thing was mostly hype and they still need human devs for now.

Aravind Srinivas We were snubbed.