Phi 3 running on your browser!

100% local, powered by WebGPU & Rust 🦀

🚨BREAKING: US National Institute of Standards and Technology publishes 1st draft of its 'AI Risk Management Framework: Generative AI Profile.' Important information & quotes:

➡️This is a comprehensive document that contains an overview of risks unique to or exacerbated by generative AI (GAI) and an extensive list of…

'Please input your target species and target genes'

CRISPR-GPT is an LLM agent that helps humans design and implement gene editing experiments, providing expert guidance across the entire experimental pipeline. This is both what speeding up science looks like & a potential risk.

I keep saying, lots of old programming rules & common practices can be thrown out the window

Whoa, GitHub just redefined software engineering.

GitHub Copilot Workspace just dropped and now you can idea, code, live demo in natural language.

Here's what you need to know (and how to sign up) 👇

PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval

Prompts LLMs to generate hybrid text representations for retrieval without any additional training.

📝arxiv.org/abs/2404.18424
👨🏽‍💻github.com/ielab/PromptRe…

LLMs do math 2 > 4 LOL

Sam Altman yup called it

i do have a soft spot for gpt2

!!

gpt2-chatbot is UNDER_HYPED.

My first coding benchmark with every new foundation model is usually 'make me an asteroids style game'. They all struggle. gpt2-chatbot does not. In just 3 requests, it made a nice basic version and executed all improvements perfectly.

gpt2-chatbot is also really great at JSON mode

We’ve partnered with Financial Times to enhance news content in ChatGPT and collaborate on new AI experiences for FT readers. openai.com/blog/content-p…

'LLMs are already being used on e-commerce platforms to improve the search and recommendation process. But what happens if this very LLM powering the recommendations is manipulated?'

Parul Pandey explores the intersection of LLMs and e-commerce practices. buff.ly/3QofAWq

gpt-2-chatbot beats LLaMA 3 70B on a simple logical question in one take.

Fully local Video Summaries with llama3 on ollama. Breaks up longer videos into chunks and provides a summary. Lots of questions on the last vid so here i am fixing errors real time.

Open-source: git.new/local-vid-summ…

There's a new bill, SB-1047 'Safe and Secure Innovation for Frontier Artificial Intelligence Models Act'.

I think it could do a great deal of harm to startups, American innovation, open source, and safety. So I've written a response to the authors: 🧵
answer.ai/posts/2024-04-…

I was skeptical about the GPT2 chatbot, but it is undoubtedly more capable than opensource models and, in some cases, better than GPT4-turbo

But it is not better than Opus in my experience – curious to know what is behind it.

Also, about the gpt2-chatbot:
It does not have a…

Ok it’s definitely using GPT-4 tokenizer so I’m betting it is 4.5 as well.

Always fingerprint w anomalous tokens

GPT-4.5 probably, 8 prompt limit. Have fun. It's good.

chat.lmsys.org
model: gpt2-chatbot

gpt2-chatbot is good. really good.

but if this is gpt-4.5, I’m disappointed.