Back
Research
Load previous page…
🤖 Used Claude's Long context prompting tips guide to let it write a file contents to xml script to make it easier to compile a series of files in a project for Claude's projects and artifacts
#research docs.anthropic.com/en/docs/bu…
🤖 more robot work, but figured out how to get better results limiting num_predict for git commit messages
#research
🤖 updated
#research project to better handle context windows and even an experimental autogpt-like commands
I used Claude 3.5 Project + Artifacts to help refactor most of the Ollama + Llama 3.1
#research project. I would call it a writing bot, but I'm not building it to automate writing. It's mostly a content wrapper around the Chat interface but it's good at generating code and building off of chat history.
expanded
#research project to handle messages and history better. Also added the ability to ask one-off prompts that may not get added to the history log.
🤖 worked on my
#research project and use Claude's project + artifacts to help reactor and add a bunch of new features to it.
🤖 more working with Ollama and Llama 3.1 and working on a story writer as a good enough demo.
#research
I did some more RAG research and found as good of use-case as I could think of to try it out again.
#research
🤖 dove a little deeper into a screenshots to code tool and the results are getting much better
#research