I've been focusing a great deal of effort on command-line LLM usage, partly because there's so little attention being paid to it by anyone else – which is weird because it's such a natural fit for how prompting works I do plan to add a web UI to my LLM tool at some point though
@simonw
-
Extracting Prompts from Jupyter Notebooks Automatically
By
–
Yeah, it's probably not too hard to write code that scans through every .ipynb notebook in a folder and extracts the prompts and responses
-
Using Long Context Models to Manage Multi-File Projects
By
–
With long context models like Claude you can send an entire project – spanning multiple files – in a single prompt and then ask questions about it or ask it to rewrite sections of the code for you
-
Using LLM Claude Opus to Complete Code with Prompts
By
–
My favourite prompt from this post is still the first one. cat files_to_prompt/cli.py | llm -m opus –system 'finish this code for me' Love that we have tools that can do this now!
-
Claude Tokenizer Unavailable for Public Token Counting Tools
By
–
Neat, I like how that one includes token counting – though frustratingly it can't count Claude tokens (just OpenAI ones) because @AnthropicAI haven't released a public version of the Claude tokenizer yet
-
ChatGPT Web Interface and Code Interpreter Usage Preferences
By
–
I still do most of my casual LLM usage via the ChatGPT web interface partly out of convenience but also because that gives me Code Interpreter which I lean on for all sorts of things
-
Logging LLM Prompts to SQLite Database for Analysis
By
–
The thing I like most about using the terminal for this is that my LLM tool logs everything to a SQLite database – I have more than 2,000 logged prompt/responses now from over 100 different models Would be neat to get a notebook to log prompts globally like that as well
-
Using LLMs and ChatGPT tools: practical guide series
By
–
This is the 11th post in my ongoing series about how I use LLMs and tools like ChatGPT https://
simonwillison.net/series/using-l
lms/
… -
Claude 3 Automates Code Testing and Documentation Tasks
By
–
This is probably the most interesting Claude 3 transcript – I pipe in my entire codebase, prompt Claude to "fill out the test_files_to_prompt.py with tests", feed it a test failure for it to fix, then tell it to "Fill out the Usage section of the README"
-
Files-to-Prompt Tool: Building with Claude 3 Opus
By
–
I released a new tool called files-to-prompt, which concatenates together files and directories to help pipe them into an LLM I built it almost entirely through prompting Claude 3 Opus. Here's a detailed write-up of how I did that and what I learned: