OpenAI Changes Up ChatGPT Interface
As part of the continuing rollout of their products in testing, OpenAI has refined the ChatGPT web interface incrementally. Here’s what it looks like now: The single drop-down box has been replaced with two buttons, one for GPT 3.5 Turbo … Read more
Text-to-Image Telephone with Midjourney AI
Today we play with Midjourney’s interesting “/describe” feature. By using /describe on an uploaded image, you can get Midjourney to generate text describing the contents of the image. The text, in turn, can be used as a text-to-image prompt to … Read more
Automated Holocaust Denialism in Bing (and Bard, but not ChatGPT).
This is how over-zealous “safeguards” on AI can go wrong. Apparently, the existence of the holocaust is too controversial for Microsoft’s Bing AI. Here I’m asking about the holocaust. It starts to type out an answer with facts: I immediately … Read more
GPT-4 Browsing Mode
OpenAI has begun gracing seemingly random ChatGPT users with an enhanced version of GPT-4 with a browsing mode similar to the one it had previously released for GPT-3.5. Here’s GPT-3.5 with browsing, asked to tell me about The Servitor: The … Read more
The Servitor Given GPT-4 API Access
Finally! OK, it was only a month on the OpenAI waitlist, But a month is a long, long time in AI years, I’m sure we can all agree. Time to give the Auto-GPT a brain. GPT-4 API is now available … Read more
JARVIS: An LLM with Minions
Not unlike Auto-GPT, JARVIS is an attempt to give LLMs more reach. It is a hybrid model consisting of an LLM controller with multiple expert models used to execute its functions. I called them minions, but the designers prefer “collaborative … Read more