Tag: token
-
Simon Willison’s Weblog: A warning about tiktoken, BPE, and OpenAI models
Source URL: https://simonwillison.net/2024/Nov/21/a-warning-about-tiktoken/#atom-everything Source: Simon Willison’s Weblog Title: A warning about tiktoken, BPE, and OpenAI models Feedly Summary: A warning about tiktoken, BPE, and OpenAI models Tom MacWright warns that OpenAI’s tiktoken Python library has a surprising performance profile: it’s superlinear with the length of input, meaning someone could potentially denial-of-service you by sending you…
-
Cloud Blog: Empowering Gemini for Malware Analysis with Code Interpreter and Google Threat Intelligence
Source URL: https://cloud.google.com/blog/topics/threat-intelligence/gemini-malware-analysis-code-interpreter-threat-intelligence/ Source: Cloud Blog Title: Empowering Gemini for Malware Analysis with Code Interpreter and Google Threat Intelligence Feedly Summary: One of Google Cloud’s major missions is to arm security professionals with modern tools to help them defend against the latest threats. Part of that mission involves moving closer to a more autonomous, adaptive…
-
Hacker News: Hyrumtoken: A Go package to encrypt pagination tokens
Source URL: https://github.com/ssoready/hyrumtoken Source: Hacker News Title: Hyrumtoken: A Go package to encrypt pagination tokens Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the “hyrumtoken” Go package, which provides a method for encrypting pagination tokens in APIs. It highlights the importance of maintaining opacity for these tokens to prevent users from…
-
Hacker News: Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference
Source URL: https://cerebras.ai/blog/llama-405b-inference/ Source: Hacker News Title: Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses breakthrough advancements in AI inference speed, specifically highlighting Cerebras’s Llama 3.1 405B model, which showcases significantly superior performance metrics compared to traditional GPU solutions. This…
-
Hacker News: Qwen2.5 Turbo extends context length to 1M tokens
Source URL: http://qwenlm.github.io/blog/qwen2.5-turbo/ Source: Hacker News Title: Qwen2.5 Turbo extends context length to 1M tokens Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the introduction of Qwen2.5-Turbo, a large language model (LLM) that significantly enhances processing capabilities, particularly with longer contexts, which are critical for many applications involving AI-driven natural language…
-
Simon Willison’s Weblog: Qwen: Extending the Context Length to 1M Tokens
Source URL: https://simonwillison.net/2024/Nov/18/qwen-turbo/#atom-everything Source: Simon Willison’s Weblog Title: Qwen: Extending the Context Length to 1M Tokens Feedly Summary: Qwen: Extending the Context Length to 1M Tokens The new Qwen2.5-Turbo boasts a million token context window (up from 128,000 for Qwen 2.5) and faster performance: Using sparse attention mechanisms, we successfully reduced the time to first…
-
Simon Willison’s Weblog: Quoting Jack Clark
Source URL: https://simonwillison.net/2024/Nov/18/jack-clark/ Source: Simon Willison’s Weblog Title: Quoting Jack Clark Feedly Summary: The main innovation here is just using more data. Specifically, Qwen2.5 Coder is a continuation of an earlier Qwen 2.5 model. The original Qwen 2.5 model was trained on 18 trillion tokens spread across a variety of languages and tasks (e.g, writing,…
-
Hacker News: Will passkeys ever replace passwords? Can they? Here’s why they should
Source URL: https://www.theregister.com/2024/11/17/passkeys_passwords/ Source: Hacker News Title: Will passkeys ever replace passwords? Can they? Here’s why they should Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses the concept of passkeys as an alternative to traditional passwords, emphasizing their potential to enhance security against phishing attacks while addressing implementation challenges and user…