Tag: tokens
-
Simon Willison’s Weblog: New OpenAI feature: Predicted Outputs
Source URL: https://simonwillison.net/2024/Nov/4/predicted-outputs/ Source: Simon Willison’s Weblog Title: New OpenAI feature: Predicted Outputs Feedly Summary: New OpenAI feature: Predicted Outputs Interesting new ability of the OpenAI API – the first time I’ve seen this from any vendor. If you know your prompt is mostly going to return the same content – you’re requesting an edit…
-
Simon Willison’s Weblog: Claude 3.5 Haiku
Source URL: https://simonwillison.net/2024/Nov/4/haiku/#atom-everything Source: Simon Willison’s Weblog Title: Claude 3.5 Haiku Feedly Summary: Anthropic released Claude 3.5 Haiku today, a few days later than expected (they said it would be out by the end of October). I was expecting this to be a complete replacement for their existing Claude 3 Haiku model, in the same…
-
Docker: Docker Desktop 4.35: Organization Access Tokens, Docker Home, Volumes Export, and Terminal in Docker Desktop
Source URL: https://www.docker.com/blog/docker-desktop-4-35/ Source: Docker Title: Docker Desktop 4.35: Organization Access Tokens, Docker Home, Volumes Export, and Terminal in Docker Desktop Feedly Summary: Docker Desktop 4.35 includes organization access tokens, a new Docker product home page, terminal enhancements, Docker Desktop for Red Hat Enterprise Linux, and the performance boost from Docker VMM for Apple Silicon…
-
Hacker News: SmolLM2
Source URL: https://simonwillison.net/2024/Nov/2/smollm2/ Source: Hacker News Title: SmolLM2 Feedly Summary: Comments AI Summary and Description: Yes Summary: The text introduces SmolLM2, a new family of compact language models from Hugging Face, designed for lightweight on-device operations. The models, which range from 135M to 1.7B parameters, were trained on 11 trillion tokens across diverse datasets, showcasing…
-
Simon Willison’s Weblog: SmolLM2
Source URL: https://simonwillison.net/2024/Nov/2/smollm2/#atom-everything Source: Simon Willison’s Weblog Title: SmolLM2 Feedly Summary: SmolLM2 New from Loubna Ben Allal and her research team at Hugging Face: SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough…
-
Rekt: M2 Exchange – Rekt
Source URL: https://www.rekt.news/m2-exchange-rekt Source: Rekt Title: M2 Exchange – Rekt Feedly Summary: Welcome to the $13.7 million M2 Exchange house of horrors, where despite claiming they’ve caught their ghost, restless spirits still perform their midnight waltz. A carnival of contradictions awaits… AI Summary and Description: Yes Summary: The text provides a detailed account of a…
-
Simon Willison’s Weblog: Cerebras Coder
Source URL: https://simonwillison.net/2024/Oct/31/cerebras-coder/#atom-everything Source: Simon Willison’s Weblog Title: Cerebras Coder Feedly Summary: Cerebras Coder Val Town founder Steve Krouse has been building demos on top of the Cerebras API that runs Llama3.1-70b at 2,000 tokens/second. Having a capable LLM with that kind of performance turns out to be really interesting. Cerebras Coder is a demo…