Ian Butler
@kinglycrow.bsky.social
I do the AI. Check out https://bismuth.sh the end to end AI development tool. We focus on specifically providing a code artifact that can be handed off to engineers for review through a mix of llms, static analysis, fuzzing and custom code search.
It said you had followed me again today and I thought you already were so yeah somethings up there.
January 13, 2025 at 4:09 AM
It said you had followed me again today and I thought you already were so yeah somethings up there.
Love to see the exploration into MCTS + LLMs. I see this direction as very promising for a whole range of tasks.
December 5, 2024 at 6:07 PM
Love to see the exploration into MCTS + LLMs. I see this direction as very promising for a whole range of tasks.
I think I will probably circle back to these over the weekend after we figure out what is causing Bismuth to explode when we go to run commands a second time.
Nothing immediately jumped out to me in the code as you'll see if you watch the video so it got annoying.
Nothing immediately jumped out to me in the code as you'll see if you watch the video so it got annoying.
December 5, 2024 at 6:05 AM
I think I will probably circle back to these over the weekend after we figure out what is causing Bismuth to explode when we go to run commands a second time.
Nothing immediately jumped out to me in the code as you'll see if you watch the video so it got annoying.
Nothing immediately jumped out to me in the code as you'll see if you watch the video so it got annoying.
We run with a huge single prompt with like 20 tools and a crap ton of super detailed state information and its worked out better than any of the multi agent interactions we initially built out a few months ago. For us, empirically a single agent performs much better.
December 4, 2024 at 1:37 AM
We run with a huge single prompt with like 20 tools and a crap ton of super detailed state information and its worked out better than any of the multi agent interactions we initially built out a few months ago. For us, empirically a single agent performs much better.
The reason I ask is this, I let our tool spin for 20 minutes but it fixed everything, like everything everything. But I was kind of antsy while it was doing this.
December 4, 2024 at 1:14 AM
The reason I ask is this, I let our tool spin for 20 minutes but it fixed everything, like everything everything. But I was kind of antsy while it was doing this.