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.
That’s my co-founder 😉
1d53b12f3bc325dcfaff51a89011f01bffca951db9df363e6b5d6233f23248a5 ;)
rachelbythebay.com/w/2025/03/26...
rachelbythebay.com/w/2025/03/26...
Problems with the heap
Okay, first off, everybody breathe. Everyone is freaking out. This is not the way to do this.
rachelbythebay.com
March 28, 2025 at 12:05 AM
That’s my co-founder 😉
I'm super excited to announce that Aviso Ventures has backed Bismuth in our mission to transform enterprise software development! Aviso is led by super experienced founders who most recently exited their business Signal Sciences to Fastly for 775M
blog.bismuth.sh/blog/aviso-v...
blog.bismuth.sh/blog/aviso-v...
blog.bismuth.sh
March 18, 2025 at 6:48 PM
I'm super excited to announce that Aviso Ventures has backed Bismuth in our mission to transform enterprise software development! Aviso is led by super experienced founders who most recently exited their business Signal Sciences to Fastly for 775M
blog.bismuth.sh/blog/aviso-v...
blog.bismuth.sh/blog/aviso-v...
I genuinely like o3, it slot right into our system with no issues. It recovers from errors and makes use of our static analysis tools much better. My only issue is the context window fills up rather rapidly with reasoning tokens.
February 4, 2025 at 7:13 AM
I genuinely like o3, it slot right into our system with no issues. It recovers from errors and makes use of our static analysis tools much better. My only issue is the context window fills up rather rapidly with reasoning tokens.
Hello o3-mini. Interested to see how you play. Definitely a forced response from OAI and clearly demonstrates why competition is good for end users.
January 31, 2025 at 8:42 PM
Hello o3-mini. Interested to see how you play. Definitely a forced response from OAI and clearly demonstrates why competition is good for end users.
DeepSeek R1 is on everyone's minds. Is it the end of GPU demand, is AI cooked? Spoilers, I don't think so. Actually, it's the best time to be an application builder working with custom models, and because of that GPU demand is going to skyrocket.
www.linkedin.com/posts/iantbu...
Ian Butler on LinkedIn: Is DeepSeek R1 the end of all GPU Demand?
DeepSeek R1 is on everyone's minds. Is it the end of GPU demand, is AI cooked? Spoilers, I don't think so. Actually, it's the best time to be an application…
www.linkedin.com
January 28, 2025 at 4:25 PM
DeepSeek R1 is on everyone's minds. Is it the end of GPU demand, is AI cooked? Spoilers, I don't think so. Actually, it's the best time to be an application builder working with custom models, and because of that GPU demand is going to skyrocket.
www.linkedin.com/posts/iantbu...
Excited to be in NYC for the next few days.
January 27, 2025 at 4:34 PM
Excited to be in NYC for the next few days.
I’ve been quiet heads down for a few weeks and we’ve been super busy.
Yesterday of all days was such a whirlwind for us. I’m super excited for what’s coming next for Bismuth. I can’t say much right now, but: 📈📈📈
Yesterday of all days was such a whirlwind for us. I’m super excited for what’s coming next for Bismuth. I can’t say much right now, but: 📈📈📈
January 25, 2025 at 9:31 AM
I’ve been quiet heads down for a few weeks and we’ve been super busy.
Yesterday of all days was such a whirlwind for us. I’m super excited for what’s coming next for Bismuth. I can’t say much right now, but: 📈📈📈
Yesterday of all days was such a whirlwind for us. I’m super excited for what’s coming next for Bismuth. I can’t say much right now, but: 📈📈📈
Everytime I’m about to post a hot take I think about the near 0 value prop there is for me and then I sigh and go back to what I was doing.
The latest discussions about US immigration proves platforms like this don’t breed intellectual discussion so jumping in would be a waste. Go build.
The latest discussions about US immigration proves platforms like this don’t breed intellectual discussion so jumping in would be a waste. Go build.
December 28, 2024 at 3:25 PM
Everytime I’m about to post a hot take I think about the near 0 value prop there is for me and then I sigh and go back to what I was doing.
The latest discussions about US immigration proves platforms like this don’t breed intellectual discussion so jumping in would be a waste. Go build.
The latest discussions about US immigration proves platforms like this don’t breed intellectual discussion so jumping in would be a waste. Go build.
This has been my healthiest year in a long time, remember to take care of yourself even when you have a lot going on 👍
December 23, 2024 at 3:47 AM
This has been my healthiest year in a long time, remember to take care of yourself even when you have a lot going on 👍
Reposted by Ian Butler
While developing XBOW over the past three months, we played around with using it for bug bounties and ended up at #11 in the US on HackerOne:
December 17, 2024 at 4:17 PM
While developing XBOW over the past three months, we played around with using it for bug bounties and ended up at #11 in the US on HackerOne:
Landed our first customer this week. Super excited to keep pushing here 😁
December 12, 2024 at 4:23 AM
Landed our first customer this week. Super excited to keep pushing here 😁
Its an interesting quirk [problem to be solved] of developing with LLMs that subtle prompting changes can cause large behavioral changes. For instance we had never seen the model attempt to call two tools at once for weeks.
Now it does. And that was our bug yesterday :P
Now it does. And that was our bug yesterday :P
December 5, 2024 at 6:02 PM
Its an interesting quirk [problem to be solved] of developing with LLMs that subtle prompting changes can cause large behavioral changes. For instance we had never seen the model attempt to call two tools at once for weeks.
Now it does. And that was our bug yesterday :P
Now it does. And that was our bug yesterday :P
Okay so Day 3 was a partial solve for Bismuth and Day 4 was also a partial solve I've also introduced a bug into our test running so we hit a 400 error after every first time we ran tests which made this a bit rough.
#AdventOfCode
www.youtube.com/watch?v=czXO...
#AdventOfCode
www.youtube.com/watch?v=czXO...
A partial solve and a bug in our model client. | Advent of Code Day 4
YouTube video by BismuthOS
www.youtube.com
December 5, 2024 at 6:03 AM
Okay so Day 3 was a partial solve for Bismuth and Day 4 was also a partial solve I've also introduced a bug into our test running so we hit a 400 error after every first time we ran tests which made this a bit rough.
#AdventOfCode
www.youtube.com/watch?v=czXO...
#AdventOfCode
www.youtube.com/watch?v=czXO...
Will be back tomorrow with more Advent of Code solves with Bismuth! Time got away from me and now its 11pm
December 4, 2024 at 6:39 AM
Will be back tomorrow with more Advent of Code solves with Bismuth! Time got away from me and now its 11pm
Okay question, do you think it's better for AI to spend a long time and get everything right when programming even minutia like linting or leave some stuff messy and let you come back to it yourself quicker?
#programming #ai #devtools
#programming #ai #devtools
December 4, 2024 at 1:09 AM
Okay question, do you think it's better for AI to spend a long time and get everything right when programming even minutia like linting or leave some stuff messy and let you come back to it yourself quicker?
#programming #ai #devtools
#programming #ai #devtools
My take is that people are far too focused on building AI coding assistants that take normal people and help them make software. I want to super charge developers and give professionals ridiculous tools.
December 4, 2024 at 12:52 AM
My take is that people are far too focused on building AI coding assistants that take normal people and help them make software. I want to super charge developers and give professionals ridiculous tools.
Okay I'm back with Bismuth for #AdventOfCode Day2 Part 2 another W! Tomorrow I'm going to consolidate to one video since Bismuth is still crushing these problems with super reasonable code and I think it would be less fatiguing for people to follow along :P
www.youtube.com/watch?v=E8vw...
www.youtube.com/watch?v=E8vw...
Reactor Safety Reports? No Prob-blem! | Advent of Code Day 2 Part 2
YouTube video by BismuthOS
www.youtube.com
December 3, 2024 at 3:20 AM
Okay I'm back with Bismuth for #AdventOfCode Day2 Part 2 another W! Tomorrow I'm going to consolidate to one video since Bismuth is still crushing these problems with super reasonable code and I think it would be less fatiguing for people to follow along :P
www.youtube.com/watch?v=E8vw...
www.youtube.com/watch?v=E8vw...
We're back with Bismuth taking on #AdventOfCode Day 2 Part 1! Watch it handle something unexpected - when the files were in the wrong place, it just... figured out where they should go and fixed it on its own 🤖
Real AI autonomy in action. Full solve below!
www.youtube.com/watch?v=UnMP...
This AI Coding Assistant Did Something I Never Expected... | Advent of Code Day 2 Part 1
YouTube video by BismuthOS
www.youtube.com
December 2, 2024 at 10:19 PM
We're back with Bismuth taking on #AdventOfCode Day 2 Part 1! Watch it handle something unexpected - when the files were in the wrong place, it just... figured out where they should go and fixed it on its own 🤖
Real AI autonomy in action. Full solve below!
www.youtube.com/watch?v=UnMP...
Continuing with Bismuth (an AI coding agent) solving #AdventOfCode problems, this time Day 1 Part 2, another success!
youtu.be/HMXABkHK2YE
youtu.be/HMXABkHK2YE
Bismuth AI Solves: Advent of Code Day 1 Part 2
YouTube video by BismuthOS
youtu.be
December 2, 2024 at 4:22 AM
Continuing with Bismuth (an AI coding agent) solving #AdventOfCode problems, this time Day 1 Part 2, another success!
youtu.be/HMXABkHK2YE
youtu.be/HMXABkHK2YE
We're going to have Bismuth (our coding agent) solve #AdventOfCode problems. If you want to see how coding agents are stacking up against novel puzzles follow along!
We're going to do two videos a day, part 1 and 2 for each problem. Bismuth crushed part 1 today!
www.youtube.com/watch?v=igbb...
We're going to do two videos a day, part 1 and 2 for each problem. Bismuth crushed part 1 today!
www.youtube.com/watch?v=igbb...
Bismuth AI Solves: Advent of Code Day 1 Part 1
YouTube video by BismuthOS
www.youtube.com
December 1, 2024 at 9:06 PM
We're going to have Bismuth (our coding agent) solve #AdventOfCode problems. If you want to see how coding agents are stacking up against novel puzzles follow along!
We're going to do two videos a day, part 1 and 2 for each problem. Bismuth crushed part 1 today!
www.youtube.com/watch?v=igbb...
We're going to do two videos a day, part 1 and 2 for each problem. Bismuth crushed part 1 today!
www.youtube.com/watch?v=igbb...
I really can't wait for Starlink to roll out on more airlines. Trying to do anything on a plane continues to be terrible :/
November 27, 2024 at 11:12 PM
I really can't wait for Starlink to roll out on more airlines. Trying to do anything on a plane continues to be terrible :/
Really excited to spin up Qwen’s reasoning model and see how it does in our agent
November 27, 2024 at 9:41 PM
Really excited to spin up Qwen’s reasoning model and see how it does in our agent
Gave our first demo to a crowd of 70ish people today! Things went well! We appreciate the opportunity and are excited for people to start using our tools and libraries! Shout out to AI Tinkerers 😁
November 22, 2024 at 6:30 AM
Gave our first demo to a crowd of 70ish people today! Things went well! We appreciate the opportunity and are excited for people to start using our tools and libraries! Shout out to AI Tinkerers 😁
Super excited to announce Asimov, our open source agent framework! 🤖
Big Features:
- Robust graph execution
- Multi-LLM support
- State management
- Snapshots & middleware
- LLM-directed flows
- OTEL
Can't wait to see what you build with it ahead of Bismuth's launch! 🛠️
github.com/BismuthCloud...
Big Features:
- Robust graph execution
- Multi-LLM support
- State management
- Snapshots & middleware
- LLM-directed flows
- OTEL
Can't wait to see what you build with it ahead of Bismuth's launch! 🛠️
github.com/BismuthCloud...
GitHub - BismuthCloud/asimov
Contribute to BismuthCloud/asimov development by creating an account on GitHub.
github.com
November 21, 2024 at 11:30 PM
Super excited to announce Asimov, our open source agent framework! 🤖
Big Features:
- Robust graph execution
- Multi-LLM support
- State management
- Snapshots & middleware
- LLM-directed flows
- OTEL
Can't wait to see what you build with it ahead of Bismuth's launch! 🛠️
github.com/BismuthCloud...
Big Features:
- Robust graph execution
- Multi-LLM support
- State management
- Snapshots & middleware
- LLM-directed flows
- OTEL
Can't wait to see what you build with it ahead of Bismuth's launch! 🛠️
github.com/BismuthCloud...
I propose the term "MatrixBreaking" instead of "Jailbreaking" for messing with LLMS.
November 21, 2024 at 9:45 PM
I propose the term "MatrixBreaking" instead of "Jailbreaking" for messing with LLMS.