biobootloader Profile Banner
Scott Swingle Profile
Scott Swingle

@biobootloader

Followers
10K
Following
43K
Media
901
Statuses
5K

Father of 3, building Mentat (the github native coding agent!) @AbanteAI, prev @DeepMind

California
Joined May 2022
Don't wanna be here? Send us removal request.
@biobootloader
Scott Swingle
5 months
if you haven't tried Mentat for a while... give it a spin
2
3
23
@biobootloader
Scott Swingle
13 days
I think, therefore I must be an earlier generation model
0
1
4
@biobootloader
Scott Swingle
18 days
that’s why I’m preparing my toddlers to be athletes
@gfodor
gfodor.id
19 days
The jobs of the future will be ones where a human doing it is valued more than pure job performance. Most people who say “well, I’d never prefer a robot for *that* job” are smuggling in an assumption that the human will be better at it. Once you notice this error it’s everywhere.
0
0
2
@biobootloader
Scott Swingle
20 days
Claude doesn't know what time it is or when previous messages were, which makes it less useful for ongoing chats (i.e. it doesn't know if it's been 3 days or 3 minutes since that last message). It sometimes even just guesses a wrong time? @alexalbert__ please add message times!
1
0
2
@emollick
Ethan Mollick
22 days
I have never been more certain that if AI development stopped today, we would still have massive & rolling disruption across society & the economy for the next ten years as people figured out how to harness what models can already do. And the end of AI progress seems unlikely.
133
231
2K
@biobootloader
Scott Swingle
22 days
didn't even pause at 50%...
1
1
6
@biobootloader
Scott Swingle
2 months
20
188
3K
@GregKamradt
Greg Kamradt
2 months
@willccbb on why it's important and beautiful
0
1
12
@biobootloader
Scott Swingle
2 months
Olympic athlete (the last human job?) training going well. She’s 16 months
2
0
8
@ja3k_
ja3k
2 months
Thought of a few more things on summarization, truncation, committing and process 🧵
@ja3k_
ja3k
2 months
Sad we couldn't make the business work. Thought I'd share some of my favorite ideas of ours on agent design 🧵
3
2
33
@seconds_0
0.005 Seconds (3/694)
2 months
@ja3k_ I think you identified most of the mistakes. I think the blind spot was really undervaluing design, marketing, and sales; common pitfalls for engineering heavy teams. You guys out-engineered the field massively, but the UX held back the adoption and sales process.
0
1
8
@biobootloader
Scott Swingle
2 months
I think context windows will be enough a big chunk of context will be snippets of mistakes made previously by agents in similar situations. models will vastly improve at generalizing from these and training models with consistent/"native" memory harness/tools
@biobootloader
Scott Swingle
2 months
big unresolved question right now: will memories / continual learning be in weights or context window (via harness / memory tools) or both
1
0
7
@biobootloader
Scott Swingle
2 months
big unresolved question right now: will memories / continual learning be in weights or context window (via harness / memory tools) or both
0
0
10
@ja3k_
ja3k
2 months
Sad we couldn't make the business work. Thought I'd share some of my favorite ideas of ours on agent design 🧵
@biobootloader
Scott Swingle
2 months
We're shutting down Mentat. Thank you to our users! Many of you tell us it's your favorite coding agent. We just didn't reach sustainable growth. I'm proud of our exceptional team: @ja3k_, @granawkins, @plutobyte. Reach out if you want to talk!
9
8
147
@biobootloader
Scott Swingle
2 months
We're shutting down Mentat. Thank you to our users! Many of you tell us it's your favorite coding agent. We just didn't reach sustainable growth. I'm proud of our exceptional team: @ja3k_, @granawkins, @plutobyte. Reach out if you want to talk!
18
3
133
@biobootloader
Scott Swingle
2 months
a jump in growth rate from 0.2% to 2% sounds suspicious, but: imagine the economy HAS grown 2% year for the last 2000 years. Then 2000 years ago global GDP would have been just $0.0008 total (not per capita!)
1
0
6
@biobootloader
Scott Swingle
3 months
why LoCoDiff is the best long context benchmark: https://t.co/3kzWEdvK44
@biobootloader
Scott Swingle
8 months
LoCoDiff: Natural Long Context Code Bench can models reconstruct the current state of code files, given the diff history? - naturally interconnected content. no padding or junk context - simple generation and eval - reasoning models do the worst - except Sonnet 3.7!
0
0
1
@biobootloader
Scott Swingle
3 months
Haiku 4.5 does well on LoCoDiff: better than GPT-5, about the same as Gemini 2.5 Pro
@claudeai
Claude
3 months
Introducing Claude Haiku 4.5: our latest small model. Five months ago, Claude Sonnet 4 was state-of-the-art. Today, Haiku 4.5 matches its coding performance at one-third the cost and more than twice the speed.
1
0
4
@biobootloader
Scott Swingle
3 months
join the mentat party now! a new kind of interactive social experience!
@granawkins
Grant♟️
3 months
Introducing the Mentat Party Agent. It’s a coding agent running in the cloud that anyone can interact with - without even logging in. I started it with a simple web app with a chatroom and snake. What will it become? Up to you. mentat . ai / party https://t.co/bQY3LiPGok
0
0
4
@ja3k_
ja3k
3 months
Party chat showcases so much of what makes Mentat unique - Every chat is a group chat - Long running chats - Great mobile site
@granawkins
Grant♟️
3 months
Introducing the Mentat Party Agent. It’s a coding agent running in the cloud that anyone can interact with - without even logging in. I started it with a simple web app with a chatroom and snake. What will it become? Up to you. mentat . ai / party https://t.co/bQY3LiPGok
1
2
9