korrents

On the map

Tap a claim on the ring to put it at the centre.

← Agents like creating code but not deleting it, so cleanup has to be deliberately built into how they work.

17 connected korrents · 16 moments from 20 Aug 2025 to 3 Nov 2026.

Everything filed under code generation code generation Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Agents like creating code but not deleting it, so cleanup has to be deliberately built into how they work. Agents like creating code but not deletingit, so cleanup has to be deliberatelybuilt into how they work. Last stated a month ago 13 Oct 2026 KD Kent C. Dodds — holds since 2026-10-13 — tap for who they are Same subject: Keeping a codebase clean now pays off directly rather than aesthetically, because a coding agent will copy the patterns already in it almost exactly. — tap to centre the map on it Keeping a codebase clean now paysoff directly rather thanaesthetically, because a codingagent will copy the patterns alreadyin it almost exactly. Last stated 8 months ago 19 Mar 2026 SW Simon Willison — holds since 2026-03-19 — tap for who they are Same subject: A code-review agent works best with a clean context, sharing nothing with the coding agent beforehand. — tap to centre the map on it A code-review agent works best witha clean context, sharing nothingwith the coding agent beforehand. Last stated 7 months ago 22 Apr 2026 WY Walden Yan — holds since 2026-04-22 — 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 andpasses its tests is not enough:security, maintainability and beingable to roll it back still needhumans in the loop. Last stated 6 months ago 7 Jun 2026 TF Tony Fadell — holds since 2026-06-07 — tap for who they are Same subject: It is generally good when a coding agent decides on its own to run linting, type checks and builds. — tap to centre the map on it It is generally good when a codingagent decides on its own to runlinting, type checks and builds. Last stated a year ago 25 Aug 2025 LR Lee Robinson — holds since 2025-08-25 — tap for who they are Same subject: Making code easier to write will lead to much more software being created overall. — tap to centre the map on it Making code easier to write willlead to much more software beingcreated overall. Last stated 7 months ago 22 Apr 2026 DC David Crawshaw — holds since 2026-04-22 — tap for who they are Same subject: Asked to find a deep bug, coding agents can patch many small issues that feel like progress while steering you away from the real problem; there is still no substitute for expertise. — tap to centre the map on it Asked to find a deep bug, codingagents can patch many small issuesthat feel like progress whilesteering you away from the realproblem; there is still nosubstitute for expertise. Last stated 4 months ago 5 Aug 2026 BV Ben Vinegar — holds since 2026-08-05 — tap for who they are Same subject: Coding agents are good enough to take on a huge task without being told so. — tap to centre the map on it Coding agents are good enough totake on a huge task without beingtold so. Last stated 2 months ago 6 Oct 2026 KD Kent C. Dodds — holds since 2026-10-06 — tap for who they are Same subject: Maintaining a duplicate set of prototype code is no burden for an agent; agents are incredibly good translators between code conventions. — tap to centre the map on it Maintaining a duplicate set ofprototype code is no burden for anagent; agents are incredibly goodtranslators between codeconventions. Last stated 3 months ago 18 Aug 2026 PM Patrick Morgan — holds since 2026-08-18 — tap for who they are Same subject: A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble. — tap to centre the map on it A codebase is the most importantcontext an AI agent has, and lettingmany different models add to itwithout consistent patterns leads totrouble. Last stated 3 weeks ago 3 Nov 2026 DB Derek Briggs — holds since 2026-11-03 — 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 anycodebase from one programminglanguage to another, work that usedto take a team over a year. Last stated 4 months ago 27 Jul 2026 BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: A strong manual coding background helps developers spot algorithmic weaknesses and flaws in generated code. — tap to centre the map on it A strong manual coding backgroundhelps developers spot algorithmicweaknesses and flaws in generatedcode. Last stated a month ago 15 Oct 2026 AT Adam Tornhill — holds since 2026-10-15 — tap for who they are Same subject: AI makes it easier to hack things together, but this is not engineering. — tap to centre the map on it AI makes it easier to hack thingstogether, but this is notengineering. Last stated 2 months ago 26 Sept 2026 GO Gergely Orosz — holds since 2026-09-26 — tap for who they are Same subject: AI tools are now highly effective at generating UI code from a rough natural-language description — tap to centre the map on it AI tools are now highly effective atgenerating UI code from a roughnatural-language description Last stated 8 months ago 7 Apr 2026 CW Chris Wellons — holds since 2026-04-07 — 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 thegenerated code, what you need isconformance testing: proof that itperforms within the boundaries ofthe code it replaced. Last stated 3 months ago 12 Aug 2026 CM Charity Majors — holds since 2026-08-12 — 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 proofnecessary, because human review ofall that generated code becomes thebottleneck. Last stated 7 months ago 22 Apr 2026 MK Martin Kleppmann — holds since 2026-04-22 — tap for who they are Same subject: The increase in developers being paged outside of working hours is most likely due to a doubling of PR frequency caused by more AI-generated or AI-written code. — tap to centre the map on it The increase in developers beingpaged outside of working hours ismost likely due to a doubling of PRfrequency caused by moreAI-generated or AI-written code. Last stated 3 weeks ago 29 Oct 2026 GO Gergely Orosz — holds since 2026-10-29 — tap for who they are Same subject: The percentage of a team's code written by AI is a vanity metric. — tap to centre the map on it The percentage of a team's codewritten by AI is a vanity metric. Last stated a year ago 20 Aug 2025 ST Sarah Tavel — holds since 2025-08-20 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Agents like creating code but not deleting it, so cleanup has to be deliberately built into how they work. Last stated 13 Oct 2026 · a month ago Holds Kent C. Dodds Read this korrent →