Tap a claim on the ring to put it at the centre.
← With AI, verification has become the bottleneck in producing work,…
17 connected korrents · 18 moments from 21 Jan 2019 to 27 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under AI and human skill
AI and human skill
Everything filed under code generation
code generation
Everything filed under AI and jobs
AI and jobs
Everything filed under design
design
Everything filed under formal proof
formal proof
Everything filed under software quality
software quality
Everything filed under AI and science
AI and science Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: With AI, verification has become the bottleneck in producing work, whereas before it happened incidentally during creation. With AI, verification has become the bottleneck in producing work, whereas before it happened incidentally during creation. Last stated 3 months ago
29 Jun 2026
HH
Hamel Husain — holds since 2026-06-29 — tap for who they are
Same subject: AI has moved the programmer's bottleneck from writing code to having good design ideas, and there is no verification loop for a design idea. — tap to centre the map on it AI has moved the programmer's bottleneck from writing code to having good design ideas, and there is no verification loop for a design idea. Last stated 6 months ago
7 Apr 2026
MN
Michael Nielsen — holds since 2026-04-07 — tap for who they are
Same subject: Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code. — tap to centre the map on it Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code. Last stated 6 months ago
22 Mar 2026
NF
Nicole Forsgren — holds since 2026-03-22 — tap for who they are
Same subject: AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. — tap to centre the map on it AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. Last stated 5 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — tap for who they are
Same subject: There is a permanent trade-off in verification: an expressive language is hard to prove things about, and a language that is easy to prove things about is hard to write in. — tap to centre the map on it There is a permanent trade-off in verification: an expressive language is hard to prove things about, and a language that is easy to prove things about is hard to write in. Last stated 8 years ago
21 Jan 2019
HW
Hillel Wayne — holds since 2019-01-21 — tap for who they are
Same subject: AI engineers can achieve high output through verification and loops that enable AI to validate its work. — tap to centre the map on it AI engineers can achieve high output through verification and loops that enable AI to validate its work. Last stated a week ago
24 Sept 2026
TT
Tomasz Tunguz — holds since 2026-09-24 — tap for who they are
Same subject: As AI agents take on bigger delegated tasks, the human bottleneck shifts to writing specs and reviewing output fast, hollowing out the middle of the work. — tap to centre the map on it As AI agents take on bigger delegated tasks, the human bottleneck shifts to writing specs and reviewing output fast, hollowing out the middle of the work. Last stated 5 months ago
3 May 2026
EY
Eugene Yan — holds since 2026-05-03 — tap for who they are
Same subject: AI is already changing the scientific process by shifting bottlenecks downstream. — tap to centre the map on it AI is already changing the scientific process by shifting bottlenecks downstream. Last stated 6 days ago
27 Sept 2026
TC
Tyler Cowen — holds since 2026-09-27 — tap for who they are
Same subject: AI systems require human oversight rather than full autonomy in analysis and workflows. — tap to centre the map on it AI systems require human oversight rather than full autonomy in analysis and workflows. Last stated a year ago
5 Sept 2025
JE
Jason Evanish — holds since 2025-09-05 — tap for who they are
Same subject: A machine doing your work better than you is no reason to stop doing it, because the point of the work was never that only you could do it. — tap to centre the map on it A machine doing your work better than you is no reason to stop doing it, because the point of the work was never that only you could do it. Last stated 4 months ago
2 Jun 2026
LS
L. M. Sacasas — holds since 2026-06-02 — tap for who they are
Same subject: A skill being automated is not a reason to stop learning it: practising what machines already do is often the stepping stone to what only people can do. — tap to centre the map on it A skill being automated is not a reason to stop learning it: practising what machines already do is often the stepping stone to what only people can do. Last stated 10 months ago
18 Nov 2025
SY
Scott H. Young — holds since 2025-11-18 — tap for who they are
Same subject: A well-written email does not need an AI summary, and an executive who delegates his reading to one has stopped doing the job. — tap to centre the map on it A well-written email does not need an AI summary, and an executive who delegates his reading to one has stopped doing the job. Last stated a year ago
21 May 2025
EZ
Ed Zitron — holds since 2025-05-21 — tap for who they are
Same subject: A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. — tap to centre the map on it A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. Last stated 6 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. — tap to centre the map on it A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. Last stated a year ago
18 Aug 2025
CB
Clay Bavor — holds since 2025-08-18 — tap for who they are
Same subject: A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on. — tap to centre the map on it A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on. Last stated 4 weeks ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A model can now port essentially any codebase from one programming language to another, work that used to take a team over a year. — tap to centre the map on it A model can now port essentially any codebase from one programming language to another, work that used to take a team over a year. Last stated 2 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Agent-generated pull requests have exploded in size with no signs of slowing down — tap to centre the map on it Agent-generated pull requests have exploded in size with no signs of slowing down Last stated 2 weeks ago
16 Sept 2026
GO
Gergely Orosz — holds since 2026-09-16 — tap for who they are
Same subject: Agents are the new compilers that compile intent into fast software. — tap to centre the map on it Agents are the new compilers that compile intent into fast software. Last stated 3 weeks ago
12 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-12 — tap for who they are
At the centre
With AI, verification has become the bottleneck in producing work, whereas before it happened incidentally during creation.
Holds Read this korrent →
AI has moved the programmer's bottleneck from writing code to having good design ideas, and there is no verification loop for a design idea.
Holds
Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code.
Holds
AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck.
Holds
There is a permanent trade-off in verification: an expressive language is hard to prove things about, and a language that is easy to prove things about is hard to write in.
Holds
AI engineers can achieve high output through verification and loops that enable AI to validate its work.
Holds
As AI agents take on bigger delegated tasks, the human bottleneck shifts to writing specs and reviewing output fast, hollowing out the middle of the work.
Holds
AI is already changing the scientific process by shifting bottlenecks downstream.
Holds
AI systems require human oversight rather than full autonomy in analysis and workflows.
Holds
A machine doing your work better than you is no reason to stop doing it, because the point of the work was never that only you could do it.
Holds
A skill being automated is not a reason to stop learning it: practising what machines already do is often the stepping stone to what only people can do.
Holds
A well-written email does not need an AI summary, and an executive who delegates his reading to one has stopped doing the job.
Holds
A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
Holds
A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair.
Holds
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.
Holds
A model can now port essentially any codebase from one programming language to another, work that used to take a team over a year.
Holds
Agent-generated pull requests have exploded in size with no signs of slowing down
Holds
Agents are the new compilers that compile intent into fast software.
Holds