Tap a claim on the ring to put it at the centre.
← In an agent-written codebase the agent-written tests are equally…
17 connected korrents · 15 moments from 25 Aug 2025 to 3 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under Anthropic
Anthropic
Everything filed under developer tools
developer tools
Everything filed under software quality
software quality
Everything filed under code generation
code generation
Everything filed under LLMs
LLMs Cannot both be true In tension 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 an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. Last stated 7 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Cannot both be true: 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
In tension: In most domains agents are now better than humans at finding bugs. — tap to centre the map on it In most domains agents are now better than humans at finding bugs. Last stated 2 months ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — 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 5 months ago
7 Jun 2026
TF
Tony Fadell — holds since 2026-06-07 — 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: Writing code with a coding agent and no tests at all is indefensible, because the old objection to testing — that it is extra work you then have to maintain — no longer applies. — tap to centre the map on it Writing code with a coding agent and no tests at all is indefensible, because the old objection to testing — that it is extra work you then have to maintain — no longer applies. Last stated 7 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: Whether agent-written code needs to be good depends entirely on how long it will live: a throwaway single-page tool can be spaghetti, anything maintained cannot. — tap to centre the map on it Whether agent-written code needs to be good depends entirely on how long it will live: a throwaway single-page tool can be spaghetti, anything maintained cannot. Last stated 7 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — 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 3 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — 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: The real value of AI coding agents is in the code a developer would never have written themselves, not just what they generate for you. — tap to centre the map on it The real value of AI coding agents is in the code a developer would never have written themselves, not just what they generate for you. Last stated 8 months ago
13 Feb 2026
AK
Arvid Kahl — holds since 2026-02-13 — tap for who they are
Same subject: AI-generated code is not fully reliable and typically needs significant manual effort to keep it working correctly. — tap to centre the map on it AI-generated code is not fully reliable and typically needs significant manual effort to keep it working correctly. Last stated 4 months ago
16 Jun 2026
SW
Stephen Wolfram — holds since 2026-06-16 — tap for who they are
Same subject: A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. — tap to centre the map on it A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. Last stated 5 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — tap for who they are
Same subject: A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. — tap to centre the map on it A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. Last stated a year ago
18 Sept 2025
TL
Tobias Lütke — holds since 2025-09-18 — tap for who they are
Same subject: A new API framework that ignores how existing apps were historically built undermines its own introduction — tap to centre the map on it A new API framework that ignores how existing apps were historically built undermines its own introduction Last stated 2 months ago
31 Aug 2026
CH
Craig Hockenberry — holds since 2026-08-31 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. — tap to centre the map on it A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. Last stated 2 months ago
30 Aug 2026
EP
Eliot Peper — holds since 2026-08-30 — 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
At the centre
In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works.
Holds Read this korrent →
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
In most domains agents are now better than humans at finding bugs.
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
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
Writing code with a coding agent and no tests at all is indefensible, because the old objection to testing — that it is extra work you then have to maintain — no longer applies.
Holds
Whether agent-written code needs to be good depends entirely on how long it will live: a throwaway single-page tool can be spaghetti, anything maintained cannot.
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
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
The real value of AI coding agents is in the code a developer would never have written themselves, not just what they generate for you.
Holds
AI-generated code is not fully reliable and typically needs significant manual effort to keep it working correctly.
Holds
A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach.
Holds
A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling.
Holds
A new API framework that ignores how existing apps were historically built undermines its own introduction
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds
A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds