Nils Durner's Blog Ahas, Breadcrumbs, Coding Epiphanies

OpenAI Operator Testdrive

Operator, the browser-controlling agent, is available in most countries where ChatGPT is available except for the EU/EEA. My notes: when tasking it with something, it translates the request to a search on Microsoft Bing. The first result is visited - and it works from there the UI is a view of the remote browser and a ChatGPT conversation p... Read more...

AI and Agency: Navigating Choice and Responsibility

Agency has increasingly become a critical dimension in discussions about artificial intelligence. While AI’s rapidly growing capabilities promise convenience and efficiency, they also raise essential questions about autonomy, choice, and responsibility. Two concepts from theoretical computer science—Automata Theory and Entropy—can help illuminat... Read more...

AI Search & AI Distortion

From a BBC report, coining the term “AI Distortion”: Our researchers tested market-leading consumer AI tools – ChatGPT, Perplexity, Microsoft Copilot and Google Gemini […] The team found ‘significant issues’ with just over half of the answers generated by the assistants. The AI assistants introduced clear factual errors into around a fifth of... Read more...

RAG in practice

Studies by Salesforce Research and Google Deepmind, as well as own experiments, have previously cast fundamental doubt on RAG. Now, Richard Meng came forward and shared practical confirmation: We’ve spoken with 30 companies who developed RAG-based chatbots on PDF documents. Every single one has failed Read more...

Sharing OpenAI Deep Research

Sharing results from OpenAI Deep Research is not straightforward as simple copy & paste will cobble up attributions. What works instead is lifting the HTML fragment from ChatGPT and building a document from there. Step-by-step: In the browser version of ChatGPT, target the title in the response report. Do a left-click, open the Developer ... Read more...