Tap a claim on the ring to put it at the centre.
← In the future, humans will not find bugs in model-produced code in…
17 connected korrents · 12 moments on record from 21 Jan 2019 to 19 Sept 2026.
Everything filed under software quality
software quality
Everything filed under vibe coding
vibe coding
Everything filed under formal proof
formal proof
Everything filed under code generation
code generation
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs 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: In the future, humans will not find bugs in model-produced code in reasonable time and will only review system composition, not via PRs or line-by-line review. In the future, humans will not find bugs in model-produced code in reasonable time and will only review system composition, not via PRs or line-by-line review. Last stated today
19 Sept 2026
TB
Thorsten Ball — holds since 2026-09-19 — tap for who they are
Same subject: Verifying a simplified model rather than the real system is worth doing even though the real system will still have bugs, because the bugs you designed in never get built. — tap to centre the map on it Verifying a simplified model rather than the real system is worth doing even though the real system will still have bugs, because the bugs you designed in never get built. Last stated 2 months ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: There is no proof good code will matter in the future, since the notion is based on human ease of use and humans will not modify most code. — tap to centre the map on it There is no proof good code will matter in the future, since the notion is based on human ease of use and humans will not modify most code. Last stated today
19 Sept 2026
TB
Thorsten Ball — holds since 2026-09-19 — tap for who they are
Same subject: The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. — tap to centre the map on it The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. Last stated 2 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — tap for who they are
Same subject: Work produced by one frontier model should be reviewed by a different one, for the same reason a good programmer's work improves under a good peer's review. — tap to centre the map on it Work produced by one frontier model should be reviewed by a different one, for the same reason a good programmer's work improves under a good peer's review. Last stated 3 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — 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 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite. — tap to centre the map on it A year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite. Last stated 4 months ago
24 May 2026
DS
Dan Shipper — holds since 2026-05-24 — tap for who they are
Same subject: Tests written by a model in the same context as the change are what find the bugs; the automated tests left behind are the lesser product. — tap to centre the map on it Tests written by a model in the same context as the change are what find the bugs; the automated tests left behind are the lesser product. Last stated a year ago
25 Aug 2025
PS
Peter Steinberger — holds since 2025-08-25 — tap for who they are
Same subject: Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. — tap to centre the map on it Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced. — tap to centre the map on it If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced. Last stated a month ago
12 Aug 2026
CM
Charity Majors — holds since 2026-08-12 — tap for who they are
Same subject: It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times. — tap to centre the map on it It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times. Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — 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: A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. — tap to centre the map on it A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. Last stated 6 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A sense of achievement in software survives writing almost none of the code yourself. — tap to centre the map on it A sense of achievement in software survives writing almost none of the code yourself. Last stated 3 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out. — tap to centre the map on it A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out. Last stated 6 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: AI is making formal methods more popular without making them mainstream, moving them from about a tenth of a per cent of engineers to three tenths. — tap to centre the map on it AI is making formal methods more popular without making them mainstream, moving them from about a tenth of a per cent of engineers to three tenths. Last stated 2 months ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: Engineers are sceptical of formal methods because they were burned by CASE and UML, sold as miracle solutions and imposed on them regardless of fit. — tap to centre the map on it Engineers are sceptical of formal methods because they were burned by CASE and UML, sold as miracle solutions and imposed on them regardless of fit. Last stated 2 months ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: Formal methods are not standard practice even in high-assurance software such as medical devices and aircraft. — tap to centre the map on it Formal methods are not standard practice even in high-assurance software such as medical devices and aircraft. Last stated 8 years ago
21 Jan 2019
HW
Hillel Wayne — holds since 2019-01-21 — tap for who they are
At the centre
In the future, humans will not find bugs in model-produced code in reasonable time and will only review system composition, not via PRs or line-by-line review.
Holds Read this korrent →
Verifying a simplified model rather than the real system is worth doing even though the real system will still have bugs, because the bugs you designed in never get built.
Holds
There is no proof good code will matter in the future, since the notion is based on human ease of use and humans will not modify most code.
Holds
The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks.
Holds
Work produced by one frontier model should be reviewed by a different one, for the same reason a good programmer's work improves under a good peer's review.
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
A year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite.
Holds
Tests written by a model in the same context as the change are what find the bugs; the automated tests left behind are the lesser product.
Holds
Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before.
Holds
If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced.
Holds
It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times.
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
A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break.
Holds
A sense of achievement in software survives writing almost none of the code yourself.
Holds
A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out.
Holds
AI is making formal methods more popular without making them mainstream, moving them from about a tenth of a per cent of engineers to three tenths.
Holds
Engineers are sceptical of formal methods because they were burned by CASE and UML, sold as miracle solutions and imposed on them regardless of fit.
Holds
Formal methods are not standard practice even in high-assurance software such as medical devices and aircraft.
Holds