https://gist.github.com/cohan/7d2abfa56b2dfdaae98bf70e84c622...
All of these UIs when there's a perfectly good command line right there! The CLI is always the best way for text.
> ai what is that song with moms spaghetti
"Lose Yourself" by Eminem
Sorted.
Something like
> ai give me an index match formula to link between sheets New and Current
Then I'll tweak the output as needed to match reality. Context would probably get in the way more than it helps in this use case.
Don't expect perfection from an AI assistant, just expect it to be a little faster than tabbing to a browser or figuring it out yourself.
In Stellaris terms: https://img.imgy.org/D76l.png
different flavours: 'fix' acts as `thefuck` replacement in 30 lines of python
If anyone fancies a tinker I imagine future editions of a CLI AI having a --context to include former prompts*, --stfu|--concise to make it respond concisely (as I was originally just responding "I know mate, haha" I also need this flag adding), probably a --model= to override that bit too, maybe even a --preamble=./prompt.txt
... it definitely needs a --json flag to prompt and enforce "I only want json and I'll parse it out of the response myself if I need to"
* Not just keeping a buffer and re-sending it, I believe context asks GPT to summarise the conversation so far and then uses the output of that for context memory. It'd need some tinkering.
I'll get round to it myself eventually, for now being able to ask little things like "is it defence or defense" and "what company owns the coco pops brand" is doing me just fine
I did realise I can now potentially pipe things into and out of GPT too, but have yet to come up with a use other than outputting through TTS e.g.
> ./ai is it defence or defense | festival --tts