Tap a claim on the ring to put it at the centre.
← The models are still bad enough that if you really care about the…
17 connected korrents · 18 moments from 30 Apr 2025 to 17 Nov 2026.
Everything filed under code generation
code generation
Everything filed under vibe coding
vibe coding
Everything filed under SaaS
SaaS
Everything filed under humility
humility
Everything filed under LLMs
LLMs
Everything filed under design
design
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: The models are still bad enough that if you really care about the final quality of what you are shipping, you probably have to look at the code.
The models are still bad enough that if you really care about the final quality of what you are shipping, you probably have to look at the code.
Last stated 7 months ago
14 Apr 2026
BL
Brian Lovin — holds since 2026-04-14 — tap for who they are
Same subject: Engineers should still look at the code they ship, especially to understand its architecture. — tap to centre the map on it
Engineers should still look at the code they ship, especially to understand its architecture.
Last stated a month ago
11 Oct 2026
LR
Lee Robinson — holds since 2026-10-11 — tap for who they are
Same subject: The model's code is now much better than the code he would have written himself. — tap to centre the map on it
The model's code is now much better than the code he would have written himself.
Last stated 6 months ago
26 May 2026
BC
Boris Cherny — holds since 2026-05-26 — tap for who they are
Same subject: That AI lets anyone prototype does not mean everyone should be shipping code to production. — tap to centre the map on it
That AI lets anyone prototype does not mean everyone should be shipping code to production.
Last stated 4 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — tap for who they are
Same subject: There is no point arguing about whether or when engineers will ship code they have not read; the only useful question is what it would take. — tap to centre the map on it
There is no point arguing about whether or when engineers will ship code they have not read; the only useful question is what it would take.
Last stated 3 months ago
12 Aug 2026
CM
Charity Majors — holds since 2026-08-12 — tap for who they are
Same subject: Software should be allowed to be finished, the way a knife or an album is, and the customer who bought the old version should get to keep it. — tap to centre the map on it
Software should be allowed to be finished, the way a knife or an album is, and the customer who bought the old version should get to keep it.
Last stated 4 months ago
26 Jul 2026
DH
David Heinemeier Hansson — holds since 2026-07-26 — tap for who they are
Same subject: Do not assume how good a model will or will not be at the thing you want it to do. — tap to centre the map on it
Do not assume how good a model will or will not be at the thing you want it to do.
Last stated 3 months ago
11 Aug 2026
KZ
Kyle Zantos — holds since 2026-08-11 — tap for who they are
Same subject: The right response to more capable models is not more shipped features; it is spending that capability on understanding users and prototyping, so what ships actually works. — tap to centre the map on it
The right response to more capable models is not more shipped features; it is spending that capability on understanding users and prototyping, so what ships actually works.
Last stated 2 months ago
23 Sept 2026
TS
Thariq Shihipar — holds since 2026-09-23 — tap for who they are
Same subject: When what is being tested is the underlying mental model, it is probably not worth polishing, because the thing might not make sense; knowing when craft and polish are needed is important. — tap to centre the map on it
When what is being tested is the underlying mental model, it is probably not worth polishing, because the thing might not make sense; knowing when craft and polish are needed is important.
Last stated 5 months ago
8 Jul 2026
MC
Meaghan Choi — holds since 2026-07-08 — tap for who they are
Same subject: LLM-driven automatic QA can raise software release quality and offset quality lost to faster AI-generated code. — tap to centre the map on it
LLM-driven automatic QA can raise software release quality and offset quality lost to faster AI-generated code.
Last stated 6 months ago
7 Jun 2026
SS
Salvatore Sanfilippo — holds since 2026-06-07 — tap for who they are
Same subject: AI coding assistance now lets a programmer complete in a day work that used to take weeks. — tap to centre the map on it
AI coding assistance now lets a programmer complete in a day work that used to take weeks.
Last stated 7 months ago
26 Apr 2026
CW
Chris Wellons — holds since 2026-04-26 — tap for who they are
Same subject: AI coding got so good so fast because code is verifiable: there is a right and wrong to hill-climb against, unlike subjective tasks. — tap to centre the map on it
AI coding got so good so fast because code is verifiable: there is a right and wrong to hill-climb against, unlike subjective tasks.
Last stated 8 months ago
18 Mar 2026
JM
John Maeda — holds since 2026-03-18 — tap for who they are
Same subject: AI models for writing software improved significantly in less than a year. — tap to centre the map on it
AI models for writing software improved significantly in less than a year.
Last stated 5 days ago
17 Nov 2026
GO
Gergely Orosz — holds since 2026-11-17 — tap for who they are
Same subject: AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard. — tap to centre the map on it
AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard.
Last stated 2 years ago
30 Apr 2025
TS
Tim Sweeney — holds since 2025-04-30 — 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 7 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — 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 9 months ago
9 Feb 2026
SH
Scott Hanselman — holds since 2026-02-09 — tap for who they are
Same subject: AI-generated code can look correct yet be slightly wrong, which is why code review is so important. — tap to centre the map on it
AI-generated code can look correct yet be slightly wrong, which is why code review is so important.
Last stated 7 months ago
15 Apr 2026
LR
Lee Robinson — holds since 2026-04-15 — 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 3 months ago
19 Aug 2026
JS
Jon Seager — holds since 2026-08-19 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
The models are still bad enough that if you really care about the final quality of what you are shipping, you probably have to look at the code.
Last stated 14 Apr 2026 · 7 months ago
Holds Brian Lovin
Read this korrent →
Similar wording
Engineers should still look at the code they ship, especially to understand its architecture.
Last stated 11 Oct 2026 · a month ago
Holds Lee Robinson
Similar wording
The model's code is now much better than the code he would have written himself.
Last stated 26 May 2026 · 6 months ago
Holds Boris Cherny
Similar wording
That AI lets anyone prototype does not mean everyone should be shipping code to production.
Last stated 19 Jul 2026 · 4 months ago
Holds Elizabeth Stone
Similar wording
There is no point arguing about whether or when engineers will ship code they have not read; the only useful question is what it would take.
Last stated 12 Aug 2026 · 3 months ago
Holds Charity Majors
Similar wording
Software should be allowed to be finished, the way a knife or an album is, and the customer who bought the old version should get to keep it.
Last stated 26 Jul 2026 · 4 months ago
Holds David Heinemeier Hansson
Similar wording
Do not assume how good a model will or will not be at the thing you want it to do.
Last stated 11 Aug 2026 · 3 months ago
Holds Kyle Zantos
Similar wording
The right response to more capable models is not more shipped features; it is spending that capability on understanding users and prototyping, so what ships actually works.
Last stated 23 Sept 2026 · 2 months ago
Holds Thariq Shihipar
Similar wording
When what is being tested is the underlying mental model, it is probably not worth polishing, because the thing might not make sense; knowing when craft and polish are needed is important.
Last stated 8 Jul 2026 · 5 months ago
Holds Meaghan Choi
Same subject: code generation
LLM-driven automatic QA can raise software release quality and offset quality lost to faster AI-generated code.
Last stated 7 Jun 2026 · 6 months ago
Holds Salvatore Sanfilippo
Same subject: code generation
AI coding assistance now lets a programmer complete in a day work that used to take weeks.
Last stated 26 Apr 2026 · 7 months ago
Holds Chris Wellons
Same subject: code generation
AI coding got so good so fast because code is verifiable: there is a right and wrong to hill-climb against, unlike subjective tasks.
Last stated 18 Mar 2026 · 8 months ago
Holds John Maeda
Same subject: LLMs
AI models for writing software improved significantly in less than a year.
Last stated 17 Nov 2026 · 5 days ago
Holds Gergely Orosz
Same subject: LLMs
AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard.
Last stated 30 Apr 2025 · 2 years ago
Holds Tim Sweeney
Same subject: LLMs
AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck.
Last stated 22 Apr 2026 · 7 months ago
Holds Martin Kleppmann
Same subject: software quality
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 9 Feb 2026 · 9 months ago
Holds Scott Hanselman
Same subject: software quality
AI-generated code can look correct yet be slightly wrong, which is why code review is so important.
Last stated 15 Apr 2026 · 7 months ago
Holds Lee Robinson
Same subject: software quality
AI-generated code should be treated as untrusted until there is evidence it preserves the intended behavior.
Last stated 19 Aug 2026 · 3 months ago
Holds Jon Seager