Tap a claim on the ring to put it at the centre.
← Code quality still matters even as LLMs make writing code much faster.
17 connected korrents · 15 moments from 21 Mar 2023 to 1 Nov 2026. Nearly all of them are about software quality .
Everything filed under LLMs
LLMs
Everything filed under coding agents
coding agents
Everything filed under Apple
Apple 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: Code quality still matters even as LLMs make writing code much faster. Code quality still matters even as LLMs make writing code much faster. Last stated 4 months ago
10 Jul 2026
FS
Fabien Sanglard — holds since 2026-07-10 — tap for who they are
Same subject: Code quality still matters even as LLMs make writing code much faster — tap to centre the map on it Code quality still matters even as LLMs make writing code much faster Last stated a year ago
13 May 2025
DH
David Heinemeier Hansson — holds since 2025-05-13 — tap for who they are
Same subject: A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the whole instruction becomes: write code until these tests pass. — tap to centre the map on it A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the whole instruction becomes: write code until these tests pass. Last stated 8 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would. — tap to centre the map on it A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would. Last stated 8 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: A test suite is not strictly necessary to rebuild something. — tap to centre the map on it A test suite is not strictly necessary to rebuild something. Last stated 4 days ago
1 Nov 2026
AR
Armin Ronacher — holds since 2026-11-01 — tap for who they are
Same subject: Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is infinitely harder to evolve software that has users. — tap to centre the map on it Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is infinitely harder to evolve software that has users. Last stated 3 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — 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 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Aiming for superhuman code quality may not be a realistic path. — tap to centre the map on it Aiming for superhuman code quality may not be a realistic path. Last stated 4 months ago
30 Jun 2026
AT
Adam Tornhill — holds since 2026-06-30 — tap for who they are
Same subject: Apple has more reason to stumble now than ever: terribly behind on AI, faltering software quality, rivals catching up on silicon, and a leadership too old to relearn. — tap to centre the map on it Apple has more reason to stumble now than ever: terribly behind on AI, faltering software quality, rivals catching up on silicon, and a leadership too old to relearn. Last stated a year ago
12 Jul 2025
DH
David Heinemeier Hansson — holds since 2025-07-12 — tap for who they are
Same subject: "Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value. — tap to centre the map on it "Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value. Last stated 3 months ago
17 Aug 2026
JC
John Cutler — holds since 2026-08-17 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 10 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 9 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. — tap to centre the map on it An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. Last stated 4 years ago
21 Mar 2023
BC
Bryan Caplan — holds since 2023-03-21 — tap for who they are
Same subject: Agents working locally can be far more powerful than any private walled garden that exists out there in the cloud. — tap to centre the map on it Agents working locally can be far more powerful than any private walled garden that exists out there in the cloud. Last stated 4 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — 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 6 months ago
26 Apr 2026
CW
Chris Wellons — holds since 2026-04-26 — tap for who they are
Same subject: AI has changed software development enough that some old assumptions about it no longer hold. — tap to centre the map on it AI has changed software development enough that some old assumptions about it no longer hold. Last stated 10 months ago
15 Jan 2026
SK
Steve Klabnik — holds since 2026-01-15 — tap for who they are
At the centre
Code quality still matters even as LLMs make writing code much faster.
Holds Read this korrent →
Code quality still matters even as LLMs make writing code much faster
Holds
A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the whole instruction becomes: write code until these tests pass.
Holds
A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would.
Holds
A test suite is not strictly necessary to rebuild something.
Holds
Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is infinitely harder to evolve software that has users.
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
Aiming for superhuman code quality may not be a realistic path.
Holds
Apple has more reason to stumble now than ever: terribly behind on AI, faltering software quality, rivals catching up on silicon, and a leadership too old to relearn.
Holds
"Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
Holds
Agents working locally can be far more powerful than any private walled garden that exists out there in the cloud.
Holds
AI coding assistance now lets a programmer complete in a day work that used to take weeks.
Holds
AI has changed software development enough that some old assumptions about it no longer hold.
Holds