Tag: model options
-
Simon Willison’s Weblog: Quoting Ethan Mollick
Source URL: https://simonwillison.net/2025/Aug/9/ethan-mollick/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Ethan Mollick Feedly Summary: The issue with GPT-5 in a nutshell is that unless you pay for model switching & know to use GPT-5 Thinking or Pro, when you ask “GPT-5” you sometimes get the best available AI & sometimes get one of the worst AIs…
-
Cloud Blog: Understand why your metrics moved with contribution analysis in BigQuery ML, now GA
Source URL: https://cloud.google.com/blog/products/data-analytics/bigquery-ml-contribution-analysis-models-now-ga/ Source: Cloud Blog Title: Understand why your metrics moved with contribution analysis in BigQuery ML, now GA Feedly Summary: The key to effective data-driven decision making is quickly processing and extracting insights from large amounts of data. However, doing this efficiently and at scale is a challenge. Imagine a retail scenario where…
-
Simon Willison’s Weblog: Long context support in LLM 0.24 using fragments and template plugins
Source URL: https://simonwillison.net/2025/Apr/7/long-context-llm/#atom-everything Source: Simon Willison’s Weblog Title: Long context support in LLM 0.24 using fragments and template plugins Feedly Summary: LLM 0.24 is now available with new features to help take advantage of the increasingly long input context supported by modern LLMs. (LLM is my command-line tool and Python library for interacting with LLMs,…
-
Wired: Hands-On With GPT-4.5, OpenAI’s Most Powerful Model Yet
Source URL: https://www.wired.com/story/gpt-4-5-openai-first-impressions/ Source: Wired Title: Hands-On With GPT-4.5, OpenAI’s Most Powerful Model Yet Feedly Summary: The release of OpenAI’s biggest model ever exposes the tension between building artificial general intelligence and making ChatGPT into a truly useful utility. AI Summary and Description: Yes **Summary:** The text discusses the release of OpenAI’s GPT-4.5 model, emphasizing…
-
Simon Willison’s Weblog: Run LLMs on macOS using llm-mlx and Apple’s MLX framework
Source URL: https://simonwillison.net/2025/Feb/15/llm-mlx/#atom-everything Source: Simon Willison’s Weblog Title: Run LLMs on macOS using llm-mlx and Apple’s MLX framework Feedly Summary: llm-mlx is a brand new plugin for my LLM Python Library and CLI utility which builds on top of Apple’s excellent MLX array framework library and mlx-lm package. If you’re a terminal user or Python…
-
Hacker News: ASTRA: HackerRank’s coding benchmark for LLMs
Source URL: https://www.hackerrank.com/ai/astra-reports Source: Hacker News Title: ASTRA: HackerRank’s coding benchmark for LLMs Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text discusses the HackerRank’s ASTRA benchmark focused on evaluating advanced AI models’ performance in real-world coding tasks, particularly for front-end development. It highlights the benchmark’s methodologies, findings on model performance, and insights…