foolishbard

Much love to Bret. Dynamicland represents such a big shift in traditional computing.

There's a chance that these systems can actually out perform their training data and be better than the sum of their parts. New work out Harvard talks about this idea of "transcendence" https://arxiv.org/abs/2406.11741

While this is a new area, it would be naive to write this off as just science fiction.

Anthropic is too new to have built that functionality I guess. Only found out because they were mad that my key was abusing their ToS and they notified the organization owner.

I searched everywhere for any other leaks of it and found nothing.

I'd say anybody who is working in the field has this expectation. But the outside observer who is excited to try a new model does not expect it.

You can build apps hosted on HF which access third party APIs, e.g. OpenAI or Anthropic. The api keys for these are then stored in the HF secrets

My anthropic key was leaked and someone ran up a 10k bill on it. Are HF going to cover that?

All3D.ai | San Francisco, CA | 75%-100% time | Machine Learning Engineer | Remote (in USA)

All3D is a 3D generative platform, built to supply 3D assets to ecommerce businesses. We've been around for four years and have reached PMF, looking to bring on additional ML talent to automate more of the workflow.

If you are familiar with the difference between NeRF and NeuS, then you'll be a great candidate. Background in diffusion models is a requirement.

Reach out to me here: kaiser at all3d dot ai

SEEKING FREELANCER

All3D | San Francisco, CA | Full-time or 75%+ | Machine Learning Engineer | Remote (in USA)

All3d is a 3D generative platform, built to supply 3D assets to ecommerce businesses. We've been around for four years and have reached PMF, looking to bring on additional ML talent to automate more of the workflow.

If you are familiar with the difference between NeRF and NeuS, then you'll be a great candidate. Background in diffusion models is a requirement.

Reach out to me here: kaiser at all3d dot ai

All3D | San Francisco, CA | Full-time or 75%+ | Machine Learning Engineer | Remote (in USA) All3d is a 3D generative platform, built to supply 3D assets to ecommerce businesses. We've been around for four years and have reached PMF, looking to bring on additional ML talent to automate more of the workflow.

If you are familiar with the difference between NeRF and NeuS, then you'll be a great candidate. Background in diffusion models is a requirement.

Reach out to me here: kaiser at all3d dot ai

I have been using sllim (note: I am the author) which allows me to easily parallelize the network requests to speed up agents.

It is only helpful with distributed chains (like tree of thoughts) and doesn't help with sequential chains.

link: https://news.ycombinator.com/item?id=36913492

Seeking Work | Remote | NLP and LLM Specialist

I am an NLP focused consultant. Previously, I've worked with small startups build value-add ML projects and design data flows which help set the foundation for future ML products.

I use the latest tools and state of the art research to take a problem from inception to production-ready code and models. My practical experience as a founder helps me connect to the startup mentality of always providing value.

Email: kaiser@pister.dev Resume: https://pister.dev/files/resume.pdf (https://pister.dev)

I was inspired by your comment and took a look at Daniel's work.

Forked it and spent the day upgrade to Aesara (the maintained Theano fork) and python3.

Haven't fully trained/tested the model, but feel free to take a look: https://github.com/kpister/biaxial-rnn-music-composition