brilliant
A rat can run a restaurant, but can an agent run a bakery?
Welcome to The Great Business Bake Off: our AI Agent Hackathon.
On December 11, you and your agents get five hours to make the most profitable bakery in town.
Spots are limited: theoryvc.com/bakeoff
0
0
3
149
Devin Stein retweeted
I can confidently say that humans were not very good at writing secure infrastructure. The endstate will be hypersecure infrastructure and software for all, but we're going to go through some turbulence before we reach that.
1,050
627
14,719
1,374,813
Devin Stein retweeted
Your agent opened the PR but did it do a good job? @devstein64 on what to benchmark: token spend, backtracking, human intervention and unproductive tool calls
1
2
4
178
"create a song for every feature release"
Introducing Suno MCP Beta
Create songs from wherever you get inspired. No tab-switching needed.
Get early access:
sunomusic.typeform.com/to/JMPYxZqQ
0
0
4
365
if coding agents are running in their own cloud environment and verifying their work before pushing, do we even need a separate CI system?
3
1
2
262
related I feel @OpenAI was right, but a little too early with Symphony github.com/openai/symphony
I'm starting to feel that @linear should be for human planning + tracking and there should be a separate ticketing system for agents
0
0
3
208
JetBrains studied 4,782 real coding-agent sessions.
~94% of SWE-Bench Pro tasks are features or bug fixes. In real use, that’s under half. The rest: explaining code, planning, reviews.
No benchmark is universal. Measure how your team uses agents.
~94% of SWE-Bench Pro tasks are features or bug fixes. In real use, that’s under half. The rest: explaining code, planning, reviews.
No benchmark is universal. Measure how your team uses agents.
7
1
9
407
I'm starting to feel that @linear should be for human planning + tracking and there should be a separate ticketing system for agents
2
1
33
6,473
regret not buying duet.ai back when I had the chance in 2023 💸
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
1
1
8
582