Tap a claim on the ring to put it at the centre.
← AI engineers can achieve high output through verification and loops that enable AI to validate its work.
17 connected korrents · 16 moments from 18 Aug 2025 to 24 Sept 2026.
Everything filed under software quality
software quality
Everything filed under LLMs
LLMs
Everything filed under design
design
Everything filed under coding agents
coding agents
Everything filed under AI and human skill
AI and human skill 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: AI engineers can achieve high output through verification and loops that enable AI to validate its work. 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: Loop engineering works exactly as far as verification does: make a problem very verifiable and you can treat it as a black box and let the model run. — tap to centre the map on it Loop engineering works exactly as far as verification does: make a problem very verifiable and you can treat it as a black box and let the model run. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. — tap to centre the map on it AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. Last stated 12 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — tap for who they are
Same subject: AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's. — tap to centre the map on it AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's. Last stated 2 months ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: With AI, verification has become the bottleneck in producing work, whereas before it happened incidentally during creation. — tap to centre the map on it 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 can supply the instruction and the feedback in a practice loop, but it cannot supply the middle step, which is doing the work. — tap to centre the map on it AI can supply the instruction and the feedback in a practice loop, but it cannot supply the middle step, which is doing the work. Last stated 2 months ago
22 Jul 2026
SY
Scott H. Young — holds since 2026-07-22 — tap for who they are
Same subject: A lab under real commercial pressure cannot fool itself about whether AI makes it productive, because the output is a model launch every few months. — tap to centre the map on it A lab under real commercial pressure cannot fool itself about whether AI makes it productive, because the output is a model launch every few months. Last stated 8 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: Polished, confident-sounding AI output does not mean the underlying analysis is clear or correct. — tap to centre the map on it Polished, confident-sounding AI output does not mean the underlying analysis is clear or correct. Last stated a year ago
5 Sept 2025
JE
Jason Evanish — holds since 2025-09-05 — 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: 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 developer using AI coding tools remains responsible for reviewing the code they ship. — tap to centre the map on it A developer using AI coding tools remains responsible for reviewing the code they ship. Last stated 7 months ago
10 Mar 2026
JS
Jon Seager — holds since 2026-03-10 — tap for who they are
Same subject: A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. — tap to centre the map on it A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. Last stated 3 weeks ago
14 Sept 2026
JS
Jason Snell — holds since 2026-09-14 — tap for who they are
Same subject: AI-assisted coding will generate a lot of low-quality output that developers will need to clean up, even as it also produces good results. — tap to centre the map on it AI-assisted coding will generate a lot of low-quality output that developers will need to clean up, even as it also produces good results. Last stated 8 months ago
9 Feb 2026
SH
Scott Hanselman — holds since 2026-02-09 — tap for who they are
Same subject: AI-generated code should be treated as untrusted until there is evidence it preserves the intended behavior. — tap to centre the map on it AI-generated code should be treated as untrusted until there is evidence it preserves the intended behavior. Last stated a month ago
19 Aug 2026
JS
Jon Seager — holds since 2026-08-19 — tap for who they are
Same subject: Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal. — tap to centre the map on it Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal. Last stated 5 months ago
7 May 2026
DC
David Crawshaw — holds since 2026-05-07 — tap for who they are
Same subject: A team that slows down and reads every pull request and every line of code should expect only a 30 to 50 percent productivity lift from AI. — tap to centre the map on it A team that slows down and reads every pull request and every line of code should expect only a 30 to 50 percent productivity lift from AI. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop. — tap to centre the map on it Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop. Last stated 4 months ago
7 Jun 2026
TF
Tony Fadell — holds since 2026-06-07 — tap for who they are
Same subject: Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great. — tap to centre the map on it Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
At the centre
AI engineers can achieve high output through verification and loops that enable AI to validate its work.
Holds Read this korrent →
Loop engineering works exactly as far as verification does: make a problem very verifiable and you can treat it as a black box and let the model run.
Holds
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
Holds
AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's.
Holds
With AI, verification has become the bottleneck in producing work, whereas before it happened incidentally during creation.
Holds
AI can supply the instruction and the feedback in a practice loop, but it cannot supply the middle step, which is doing the work.
Holds
A lab under real commercial pressure cannot fool itself about whether AI makes it productive, because the output is a model launch every few months.
Holds
Polished, confident-sounding AI output does not mean the underlying analysis is clear or correct.
Holds
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
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 developer using AI coding tools remains responsible for reviewing the code they ship.
Holds
A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta.
Holds
AI-assisted coding will generate a lot of low-quality output that developers will need to clean up, even as it also produces good results.
Holds
AI-generated code should be treated as untrusted until there is evidence it preserves the intended behavior.
Holds
Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal.
Holds
A team that slows down and reads every pull request and every line of code should expect only a 30 to 50 percent productivity lift from AI.
Holds
Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop.
Holds
Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great.
Holds