Quick reality check on Quivr, a tool to: Dump all your files and chat with it using your Generative AI Second Brain using LLMs (GPT 3.5/4, Private, Anthropic, VertexAI) & Embeddings There has been a seemingly endless stream of such projects over the last several months. The core concept is always the same, but the newest incarnations di... Read more 12 Jul 2023 - 2 minute read
Anthropic have released Claude 2, touting “two times better at giving harmless answers”. Initial reactions on the web seem favorable, particularly regarding the support of larger documents that ChatGPT. What I have seen so far with the regular end-user chat UI: A book of 1027 pages didn’t load: “Text extraction failed”. Loading a 62-pages le... Read more 12 Jul 2023 - 1 minute read
Non-uniform performance reported for in-context learning: How Language Models Use Long Contexts: Model performance is highest when relevant information occurs at the beginning or end of its input context Model performance substantially decreases as input contexts grow longer Extended-context models are not necessarily better at using i... Read more 10 Jul 2023 - 1 minute read
GPT-4 API was just made generally available, and: We are working on safely enabling fine-tuning for GPT-4 and GPT-3.5 Turbo and expect this feature to be available later this year. Source Also: Developers wishing to continue using their fine-tuned models beyond January 4, 2024 will need to fine-tune replacements atop the new base GPT-... Read more 07 Jul 2023 - 1 minute read
Prompted by a colleague posting the Handelblatt article about SAP investing in Aleph Alpha, I elaborated that the beauty of Aleph Alpha is GDPR-compliance and generally good data hygiene. With OpenAI, for me it’s oftentimes a “write code to do X”, with X actually being done on data that sits with me locally. But if X requires advanced natural la... Read more 01 Jul 2023 - less than 1 minute read