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 The problems he shares are familiar: ... Read more 11 Feb 2025 - less than 1 minute read
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 08 Feb 2025 - 1 minute read
A “Virtual Sales Associate” was showcased briefly by OpenAI, perhaps as something like GPTs: “Enterprises can start to customize these applications [agents?]”. Also, OpenAI may be going after the data inside organizations: “The most valuable data is the data you have in your company. You can imagine us to expand Deep Research to internal informa... Read more 06 Feb 2025 - 1 minute read
To continue the trend of “long-running AI”, OpenAI have launched “Deep Research” (not in the EU, though): Deep research is OpenAI’s next agent that can do work for you independently—you give it a prompt, and ChatGPT will find, analyze, and synthesize hundreds of online sources to create a comprehensive report at the level of a research analys... Read more 03 Feb 2025 - less than 1 minute read
OpenAI have released o3-mini. It’s the first model that scores below 1% on the Vectara Hallucination Benchmark. This is in stark contrast to DeepSeek R1, which is off their chart at 14.3% hallucination and underperforming small language models like Amazon Titan Express. o3-mini comes in three strenghes, determined by the “reasoning effort” (dubb... Read more 02 Feb 2025 - less than 1 minute read