In the LLM frontend comparison for my article on process visualization, I have included whether or not the particular frontend includes support for PDF files. Some of the frontends considered do so only poorly: either they only use the text portion, or the PDF gets pre-processed through RAG. OpenAI have now added the capability to process PDF fi... Read more 19 Mar 2025 - less than 1 minute read
Several outlets report about Russian propaganda agencies poising AI training data, citing Newsguard: An audit found that the 10 leading generative AI tools advanced Moscow’s disinformation goals by repeating false claims from the pro-Kremlin Pravda network 33 percent of the time They only seem to have published 5 out of the 15 questions the... Read more 19 Apr 2025 (Updated) - 3 minute read
OpenAI have made additional agentic features available to developers: Web Search, File Search, Computer Use and an SDK that improves on Swarm (Announcement). The “Computer Use” API gives access to the CUA model, which also powers OpenAI Operator. My notes on this: fixed “Bing search: OpenAI news” with initial screenshot demo script here th... Read more 13 Mar 2025 - less than 1 minute read
Ethan Mollick recently shared a tongue-in-cheek remark on how to choose between various ChatGPT “models” (LinkedIn, X, Bluesky). My inital suggestion of creating a decision chart to simplify navigating the ChatGPT user interface had received positive feedback, so I have created a first draft here. Meanwhile, Peter Gostev compiled a “Feature Stat... Read more 06 Mar 2025 - less than 1 minute read
OpenAI have released GPT 4.5 in preview: GPT‑4.5 is a very large and compute-intensive model, making it more expensive than and not a replacement for GPT‑4o. The System Card remarks reduced hallucination, practical use on the API confirms it’s also much slower in terms of tokens per second. Priced at $75.00 $37.50/$150.00 (input/output), i... Read more 28 Feb 2025 (Updated) - 1 minute read