Anyone curious about automatically pulling together query responses from multiple chatbots might want to explore Alan's open-source Botwell project. I’ve found it really eye-opening and worth a look at https://github.com/alanwilhelm/botwell/tree/main
Thanks Alan for your automating chatbot queries and have them grade each other, paving the way for a Boswell Test that leaves writers feeling "lost without their trusty AI writing companion."
Anyone curious about automatically pulling together query responses from multiple chatbots might want to explore Alan's open-source Botwell project. I’ve found it really eye-opening and worth a look at https://github.com/alanwilhelm/botwell/tree/main
Peter's Boswell test in action: https://news.ycombinator.com/item?id=43196405
Hello Peter! This is one of my favorite ongoing performance benchmarks. It is very code focused but that's my main use case. https://aider.chat/2024/12/21/polyglot.html#the-polyglot-benchmark
Thanks Alan for your automating chatbot queries and have them grade each other, paving the way for a Boswell Test that leaves writers feeling "lost without their trusty AI writing companion."