muds 4 hours agoInteresting work. Is this a wrapper around the AUTOLEAN project (https://github.com/T3S1AMAX/autolean)?
eisbaw 3 hours agothe tricky bit is ensuring your inaccurate plain english statement is captured and formalized correctly as lean.
owlbite 3 hours agoInteresting, but I don't see any licensing terms, which means I can't touch it in a commercial setting.jrflo an hour agoWhat commercial setting do you want to use a Lean theorem-proving agent in?a2ff6eeb0 2 hours agoIt's AI generated, so licensing terms are unenforceable.
philipfweiss 2 hours agoMaybe consider an integration with theoremdb.org?fractorial an hour agoTo be clear, I am deep into auto-research, but hooking up slop to slop is just unlikely to produce anything valuable.Value is in how maths is communicated: The process, frustrations, triumphs, etc.We have to able to take generated formalizations from “it compiles” to “it is correct” before crystallizing them.
fractorial an hour agoTo be clear, I am deep into auto-research, but hooking up slop to slop is just unlikely to produce anything valuable.Value is in how maths is communicated: The process, frustrations, triumphs, etc.We have to able to take generated formalizations from “it compiles” to “it is correct” before crystallizing them.
homarp 5 hours agoA terminal AI coding assistant with a built-in math formalization engine — describe a problem in plain language and it converts it into a Lean 4 theorem and attempts a formal proof.seunosewa 4 hours agoCould you provide a practical example?rawland 4 hours agoThere is one in the quickstart: mathcode -p "prove that the square of an even number is even" https://math-ai-org.github.io/mathcode/#quickstart - if you look very closely, the screenshot at the top actually shows the output (and the solution).
seunosewa 4 hours agoCould you provide a practical example?rawland 4 hours agoThere is one in the quickstart: mathcode -p "prove that the square of an even number is even" https://math-ai-org.github.io/mathcode/#quickstart - if you look very closely, the screenshot at the top actually shows the output (and the solution).
rawland 4 hours agoThere is one in the quickstart: mathcode -p "prove that the square of an even number is even" https://math-ai-org.github.io/mathcode/#quickstart - if you look very closely, the screenshot at the top actually shows the output (and the solution).
129387 4 hours ago[dead]eisbaw 3 hours agogit clone is slightly fastergumby 3 hours agoAnd doesn’t use as many tokens, at least for now.black_knight an hour agoI just replaced git clone with a script which fetches the README.md and sets of a fleet of agents to do a cleanroom reimplementation.Lets me ignore the LICENSE.md file, and use how I want.
eisbaw 3 hours agogit clone is slightly fastergumby 3 hours agoAnd doesn’t use as many tokens, at least for now.black_knight an hour agoI just replaced git clone with a script which fetches the README.md and sets of a fleet of agents to do a cleanroom reimplementation.Lets me ignore the LICENSE.md file, and use how I want.
gumby 3 hours agoAnd doesn’t use as many tokens, at least for now.black_knight an hour agoI just replaced git clone with a script which fetches the README.md and sets of a fleet of agents to do a cleanroom reimplementation.Lets me ignore the LICENSE.md file, and use how I want.
black_knight an hour agoI just replaced git clone with a script which fetches the README.md and sets of a fleet of agents to do a cleanroom reimplementation.Lets me ignore the LICENSE.md file, and use how I want.
Interesting work. Is this a wrapper around the AUTOLEAN project (https://github.com/T3S1AMAX/autolean)?
the tricky bit is ensuring your inaccurate plain english statement is captured and formalized correctly as lean.
Interesting, but I don't see any licensing terms, which means I can't touch it in a commercial setting.
What commercial setting do you want to use a Lean theorem-proving agent in?
It's AI generated, so licensing terms are unenforceable.
Maybe consider an integration with theoremdb.org?
To be clear, I am deep into auto-research, but hooking up slop to slop is just unlikely to produce anything valuable.
Value is in how maths is communicated: The process, frustrations, triumphs, etc.
We have to able to take generated formalizations from “it compiles” to “it is correct” before crystallizing them.
A terminal AI coding assistant with a built-in math formalization engine — describe a problem in plain language and it converts it into a Lean 4 theorem and attempts a formal proof.
Could you provide a practical example?
There is one in the quickstart:
https://math-ai-org.github.io/mathcode/#quickstart - if you look very closely, the screenshot at the top actually shows the output (and the solution).[dead]
git clone is slightly faster
And doesn’t use as many tokens, at least for now.
I just replaced git clone with a script which fetches the README.md and sets of a fleet of agents to do a cleanroom reimplementation.
Lets me ignore the LICENSE.md file, and use how I want.