AI/ML

AI/ML

1849 bookmarks
Custom sorting
Suno
Suno
Suno is building a future where anyone can make great music.
·suno.com·
Suno
Superhuman?
Superhuman?
What does it mean for AI to be better than a human? And how can we tell?
·oneusefulthing.org·
Superhuman?
Hallucination-Free RAG: Making LLMs Safe for Healthcare
Hallucination-Free RAG: Making LLMs Safe for Healthcare
LLMs have the potential to revolutionise our field of healthcare, but the fear and reality of hallucinations prevent adoption in most applications.
·mattyyeung.github.io·
Hallucination-Free RAG: Making LLMs Safe for Healthcare
Freeing the chatbot
Freeing the chatbot
Intelligence, of a sort, is going to be all around us
·oneusefulthing.org·
Freeing the chatbot
Chatbots Have Thoroughly Infiltrated Scientific Publishing
Chatbots Have Thoroughly Infiltrated Scientific Publishing
One percent of scientific articles published in 2023 showed signs of generative AI’s potential involvement, according to a recent analysis
·scientificamerican.com·
Chatbots Have Thoroughly Infiltrated Scientific Publishing
GitHub - truefoundry/cognita: RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
GitHub - truefoundry/cognita: RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry - GitHub - truefoundry/cognita: RAG (Retrieval Augmented Generation) Fra...
·github.com·
GitHub - truefoundry/cognita: RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Snowflake Arctic Cookbook
Snowflake Arctic Cookbook
Today's big model release was Snowflake Arctic, an enormous 480B model with a 128×3.66B MoE (Mixture of Experts) architecture. It's Apache 2 licensed and Snowflake state that "in addition, we …
·simonwillison.net·
Snowflake Arctic Cookbook
What can LLMs never do?
What can LLMs never do?
On goal drift and lower reliability. Or, why can't LLMs play Conway's Game Of Life?
·strangeloopcanon.com·
What can LLMs never do?
James Grimmelmann (@jtlg@mastodon.lawprofs.org)
James Grimmelmann (@jtlg@mastodon.lawprofs.org)
Something exceptionally grim is happening on the Internet. In the last few months, the constant flood of algorithmically generated junk content has kicked into an AI-powered overdrive, and it is cutting a swath of destruction as it overwhelms search engines, filters, and moderation systems Call it Gresham's Law 2.0: bad content drives out good. I'm starting this thread to document it, because there is a *lot* happening all at once. #greshamslaw20
·mastodon.lawprofs.org·
James Grimmelmann (@jtlg@mastodon.lawprofs.org)
GitHub - timpaul/form-extractor-prototype
GitHub - timpaul/form-extractor-prototype

This tool extracts the structure from an image of a form.

It uses the Claude 3 LLM model by Anthropic.

A single extraction of an A4 form page costs about 10p.

It replicates the form structure in JSON, following the schema used by GOV.UK Forms.

It then uses that to generate a multi-page web form in the GOV.UK style.

·github.com·
GitHub - timpaul/form-extractor-prototype
WHY AI Works - YouTube
WHY AI Works - YouTube
Bertrand Serlet's thoughts on WHY LLMs and AI in general work so well, nowadays.
·m.youtube.com·
WHY AI Works - YouTube
LLMs and the Harry Potter problem
LLMs and the Harry Potter problem
Large language models may have big context windows, but they still aren't good enough at using the information in big contexts, especially in high value use-cases.
·pyqai.com·
LLMs and the Harry Potter problem
openelm/README-pretraining.md
openelm/README-pretraining.md
Apple released something big three hours ago, and I'm still trying to get my head around exactly what it is. The parent project is called CoreNet, described as "A library …
·simonwillison.net·
openelm/README-pretraining.md