Cloud LLM Workbenches Some of the additions to my chatbots/workbenches in recent months: streaming mode multi-modal input box: allows pasting images from the clipboard straight cleaner interface support for PDF files not just text, truly multi-modal no RAG, so works for all use-cases new mod... Read more 19 Sep 2024 - 1 minute read
So OpenAI have released a preview of their new O1 model(s): Landing Page. This is a specialized model and departs from the tradition of the other GPT models. It is available to paid ChatGPT subscribers, to Tier 5 API customers and via OpenRouter. What’s special about the O1 model family is that, in marketing speak, “spend more time thinking thr... Read more 17 Sep 2024 (Updated) - 3 minute read
Peter Gostev, Head of AI at Moonpig, shared his excitement about Replit’s new AI coding Agent. He highlighted three key features: Cloud-based IDE with managed environments An AI agent that not only generates code but also installs packages and manages files Easy deployment of apps from Replit While this sounds promising for streamlinin... Read more 08 Sep 2024 - 1 minute read
(TLDR; I tried device-local Whisper and ended up using Google Gemini instead.) Several pain points with Apple Podcasts in particular got me interested in using Frontier Models to create a more personalized experience: Rather low audio quality for some episodes: poor (if any) post-processing without noise cancelling, lack of gain normalizatio... Read more 06 Oct 2024 (Updated) - 2 minute read
The recent news about Aleph Alpha’s strategic shift away from developing large language models (LLMs) to focus on AI integration services has sparked discussions about the state of AI deployment in Germany. While this change might seem discouraging for those hoping for a strong European contender in the AI race, it’s worth examining the practica... Read more 20 Sep 2024 (Updated) - 1 minute read