biobootloader
Joined 3 years ago
Karma
23
Submissions
15
Member since
Apr 10
Recent submissions
Comment · 1 year ago
a new social experience...
Comment · 3 years ago
Hey Paul, I'm a Mentat author.
> I also notice that the instructions prompt that mentat uses seems to be inspired by the aider benchmark? Glad to see others adopting similar benchmarking approaches.
We were inspired by you to use Exercism as a benchmark, thank you! We will add attribution for that. We switched our original instruction prompts for that benchmark to be similar to Aiders to allow for fair comparison.
> After looking around a bit, there seems to be a bunch of aider code in your repo. Some attribution would be appreciated.
We have an unused implementation of your output response format (https://github.com/AbanteAI/mentat/blob/main/mentat/parsers/...), but I don't know what else you are seeing? We implemented that to compare with our response formats and didn't find much difference in performance.
Comment · 3 years ago
we are working on creating "real world" benchmarks that require a lot of context, and will report when we have results!
Comment · 3 years ago
Yes, it uses your local files and edits for you. Let us know what you think!
Comment · 3 years ago
the idea is that mentats in dune combine human and computer skills to assist others
but yeah it is funny
Comment · 3 years ago
agreed! but it'd be nice to not have to jump back to the editor to fix a minor crash and then go rerun
Comment · 3 years ago
it will sometimes fix other bugs, but yeah the focus is on ones that caused the crash or are obvious
Comment · 3 years ago
haha yes it did feel a bit wild just letting this run on my machine!
I wouldn't recommend running it on a script that's supposed to delete files