Nils Durner's Blog Ahas, Breadcrumbs, Coding Epiphanies

[UPDATED] OpenAI Web Search, o3 API

In addition to the newly released OpenAI models, I have added Web Search to my LLM frontend. This allows up-to-date information to be worked with: Prompt: when is the new German chancellor going to be sworn in? Response: Friedrich Merz is scheduled to be elected as Germany’s new Chancellor on May 6, 2025. (reuters.com) […] Source references... Read more

Standford AI Index '25 out

The Standford HAI 2025 AI Index Report is out. Notes: “AI is increasingly embedded in everyday life. From healthcare to transportation, AI is rapidly moving from the lab to daily life. […] On the roads, self-driving cars are no longer experimental”. Examples given include Waymo and Baidu Apollo Go” However, streets signs advising t... Read more

[UPDATED] OpenAI API: 4.1 in, 4.5 out

OpenAI have announced their newest flagship model family: GPT-4.1. It comes in three sizes: GPT-4.1, 4.1-mini, and 4.1-nano. Two versions of GPT-4.1 were available in the last weeks for community testing via OpenRouter as “Optimus Alpha” and “Quasar Alpha”. There, I noticed that the gender bias sample showcased in the Stanford HAI AI Index Repo... Read more

[UPDATED] Llama 4 released

Llama 4 has been released - partially. It’s a suite of three LLMs, with the biggest model (“Behemoth”) still in training. Notes: ~apparently no restrictions on use within the EU~ [see Update below] ~trained in fp8 precision~ [see Update below] already live on OpenRouter via Together: smallest model “Scout” costlier than Gemini ... Read more

[UPDATED] GPT-4o Imagegen for infographics

Several samples on X suggest that GPT-4o Imagegen can be used for infographics (1, 2, 3, 4). In my experiments, instructions to Imagegen need to be on-point: simply supplying a Readme.md with all kinds of different notes on a code project and asking it to visualize the build process does not work - the model will even start to hallucinate random... Read more