This is not really a new idea, even I wrote "how" in rust, that just ask my local llm and after approve execute.
But the idea from OP is much better! I love that he used basic tools,
this comma remind me a little bit of old irc bot, it was exactly the same flow, ", <query>".
Love it! <3
Thanks for sharing!
BTW, no one need $7k device to run eg. gemma4 e2b, even your phone can act as llm provider, it was a joke from op ;)
btw, even his dottxt.ai, look interesting, that gives for every query to llm a schema how to respond, i always tell my llm how to respond in system prompt, but this is much cleaner!
> It was fun, easy, and only cost $7k for a M5 Max MBP with 128GB of unified memory.
Unclear to me whether this means $7k was the cost of the hardware that can run it, or if that was the token cost of implementation. The latter is surprisingly high; but the former is (to me?) a weird thing to share (if the whole point of this is that it can run locally, isn't that value undermined if it requires purchasing updated hardware to run?)
This is not really a new idea, even I wrote "how" in rust, that just ask my local llm and after approve execute.
But the idea from OP is much better! I love that he used basic tools, this comma remind me a little bit of old irc bot, it was exactly the same flow, ", <query>".
Love it! <3
Thanks for sharing!
BTW, no one need $7k device to run eg. gemma4 e2b, even your phone can act as llm provider, it was a joke from op ;)
btw, even his dottxt.ai, look interesting, that gives for every query to llm a schema how to respond, i always tell my llm how to respond in system prompt, but this is much cleaner!
$ dottxt generate --model Qwen/Qwen3.5-27B --prompt "Is this output valid?" --schema '{"valid": "boolean"}'
{"valid": true}
It was indeed inspired from my IRC days :)
Original author here, the project has evolved quite a bit since then, you can follow here if that interests you: https://github.com/rlouf/sigil
(The $7k was sarcasm)
> It was fun, easy, and only cost $7k for a M5 Max MBP with 128GB of unified memory.
Unclear to me whether this means $7k was the cost of the hardware that can run it, or if that was the token cost of implementation. The latter is surprisingly high; but the former is (to me?) a weird thing to share (if the whole point of this is that it can run locally, isn't that value undermined if it requires purchasing updated hardware to run?)
Cost of hardware. They’re running a local LLM.
Are you willing to share the script? Using the pi /share command it will publish it to a Gist on GitHub
Of course: https://github.com/rlouf/sigil
How about instead of blindly executing code, it tells you the command you should use, so you can transition to knowing these things instead?
That is exactly what it does.
My bad. The video was very small on my phone.