Tap a claim on the ring to put it at the centre.
← Models will not learn to write maintainable code from today’s…
17 connected korrents · 14 moments from 1 Feb 2002 to 22 Sept 2026. Nearly all of them are about software quality .
Everything filed under design
design
Everything filed under LLMs
LLMs
Everything filed under design
design
Everything filed under coding agents
coding agents 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: Models will not learn to write maintainable code from today’s benchmarks, because the cost of bad architecture cannot be measured by running the unit tests — it arrives three to six months later. Models will not learn to write maintainable code from today’s benchmarks, because the cost of bad architecture cannot be measured by running the unit tests — it arrives three to six months later. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Building on a model is unlike any previous software engineering, because the thing you are building on cannot be designed up front. — tap to centre the map on it Building on a model is unlike any previous software engineering, because the thing you are building on cannot be designed up front. Last stated 3 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Polished UI is a reasonable signal that a team invested comparable effort in the underlying code quality. — tap to centre the map on it Polished UI is a reasonable signal that a team invested comparable effort in the underlying code quality. Last stated 4 months ago
13 Jun 2026
NP
Nikita Prokopov — holds since 2026-06-13 — tap for who they are
Same subject: The most-cited study showing that language design affects software quality rests on misclassified repositories. — tap to centre the map on it The most-cited study showing that language design affects software quality rests on misclassified repositories. Last stated 12 years ago
7 Nov 2014
DL
Dan Luu — holds since 2014-11-07 — tap for who they are
Same subject: Great designers make it look easy, and the ease is mostly an illusion: the conversational tone of good writing comes on the eighth rewrite. — tap to centre the map on it Great designers make it look easy, and the ease is mostly an illusion: the conversational tone of good writing comes on the eighth rewrite. Last stated 25 years ago
1 Feb 2002
PG
Paul Graham — holds since 2002-02-01 — 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 7 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 7 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — 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 2 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 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation. — tap to centre the map on it A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation. Last stated 4 weeks ago
22 Sept 2026
HR
Harper Reed — holds since 2026-09-22 — 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: Impressive one-shot AI coding demos are not a good way to judge AI coding ability. — tap to centre the map on it Impressive one-shot AI coding demos are not a good way to judge AI coding ability. Last stated 9 months ago
4 Feb 2026
SH
Scott Hanselman — holds since 2026-02-04 — tap for who they are
Same subject: AI writing tools can be used for editing help without letting them take over work that has personal meaning. — tap to centre the map on it AI writing tools can be used for editing help without letting them take over work that has personal meaning. Last stated 3 months ago
27 Jul 2026
AH
Ann Handley — holds since 2026-07-27 — tap for who they are
Same subject: As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever. — tap to centre the map on it As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever. Last stated 9 months ago
4 Feb 2026
SH
Scott Hanselman — holds since 2026-02-04 — tap for who they are
Same subject: Getting genuinely original output from AI requires working hard against the grain of its defaults. — tap to centre the map on it Getting genuinely original output from AI requires working hard against the grain of its defaults. Last stated 4 months ago
29 Jun 2026
KC
Kyle Chayka — holds since 2026-06-29 — tap for who they are
Same subject: Progress toward AI autonomously solving major open scientific problems requires first mastering the organization and presentation of established knowledge in long-form writing. — tap to centre the map on it Progress toward AI autonomously solving major open scientific problems requires first mastering the organization and presentation of established knowledge in long-form writing. Last stated 2 months ago
12 Aug 2026
NL
Nathan Lambert — holds since 2026-08-12 — tap for who they are
Same subject: The thinking part of the human brain runs on under ten watts and still writes a better novel than a ten-megawatt GPU cluster. — tap to centre the map on it The thinking part of the human brain runs on under ten watts and still writes a better novel than a ten-megawatt GPU cluster. Last stated 3 years ago
9 Nov 2023
EM
Elon Musk — holds since 2023-11-09 — tap for who they are
Same subject: Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway. — tap to centre the map on it Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway. Last stated 5 months ago
28 May 2026
JF
Jacob Falkovich — holds since 2026-05-28 — tap for who they are
At the centre
Models will not learn to write maintainable code from today’s benchmarks, because the cost of bad architecture cannot be measured by running the unit tests — it arrives three to six months later.
Holds Read this korrent →
Building on a model is unlike any previous software engineering, because the thing you are building on cannot be designed up front.
Holds
Polished UI is a reasonable signal that a team invested comparable effort in the underlying code quality.
Holds
The most-cited study showing that language design affects software quality rests on misclassified repositories.
Holds
Great designers make it look easy, and the ease is mostly an illusion: the conversational tone of good writing comes on the eighth rewrite.
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
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
A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
Holds
Impressive one-shot AI coding demos are not a good way to judge AI coding ability.
Holds
AI writing tools can be used for editing help without letting them take over work that has personal meaning.
Holds
As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever.
Holds
Getting genuinely original output from AI requires working hard against the grain of its defaults.
Holds
Progress toward AI autonomously solving major open scientific problems requires first mastering the organization and presentation of established knowledge in long-form writing.
Holds
The thinking part of the human brain runs on under ten watts and still writes a better novel than a ten-megawatt GPU cluster.
Holds
Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway.
Holds