korrents

On the map

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

← AI coding got so good so fast because code is verifiable: there is a…

17 connected korrents · 18 moments from 18 Mar 2025 to 2 Nov 2026.

Everything filed under code generation code generation Everything filed under software quality software quality Everything filed under LLMs LLMs Everything filed under coding agents coding agents Everything filed under AI writing AI writing Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: AI coding got so good so fast because code is verifiable: there is a right and wrong to hill-climb against, unlike subjective tasks. AI coding got so good so fast because codeis verifiable: there is a right and wrongto hill-climb against, unlike subjectivetasks. Last stated 8 months ago 18 Mar 2026 JM John Maeda — holds since 2026-03-18 — tap for who they are Same subject: AI-written code is fine when only the visual result matters, but insufficient in technical domains where understanding what is actually being computed is required. — tap to centre the map on it AI-written code is fine when onlythe visual result matters, butinsufficient in technical domainswhere understanding what is actuallybeing computed is required. Last stated 5 months ago 16 Jun 2026 SW Stephen Wolfram — holds since 2026-06-16 — tap for who they are Same subject: AI systems are much better at tasks whose correctness can be verified than at tasks whose correctness cannot be checked. — tap to centre the map on it AI systems are much better at taskswhose correctness can be verifiedthan at tasks whose correctnesscannot be checked. Last stated 4 months ago 13 Jul 2026 AN Arvind Narayanan — holds since 2026-07-13 — tap for who they are Same subject: Anyone who knew how to code before AI is having a way better time using AI than someone who did not, because they know the right words to say. — tap to centre the map on it Anyone who knew how to code beforeAI is having a way better time usingAI than someone who did not, becausethey know the right words to say. Last stated 7 months ago 14 Apr 2026 BL Brian Lovin — holds since 2026-04-14 — tap for who they are Same subject: AI-generated code has moved from sloppy toward clean over time. — tap to centre the map on it AI-generated code has moved fromsloppy toward clean over time. Last stated a month ago 16 Oct 2026 GS Grant Sanderson — holds since 2026-10-16 — 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 codingprocess, clearly specifying goalsand exercising good judgment willmatter more than ever. Last stated 10 months ago 4 Feb 2026 SH Scott Hanselman — holds since 2026-02-04 — tap for who they are Same subject: There has never been a better time to code with AI, because there are so many repos to learn from. — tap to centre the map on it There has never been a better timeto code with AI, because there areso many repos to learn from. Last stated 2 years ago 18 Mar 2025 JM John Maeda — holds since 2025-03-18 — tap for who they are Same subject: There is a world where AI coding tools change nothing except that engineers are happier, and for a lot of companies that is not good enough to keep paying for. — tap to centre the map on it There is a world where AI codingtools change nothing except thatengineers are happier, and for a lotof companies that is not good enoughto keep paying for. Last stated 6 months ago 27 May 2026 DR Dax Raad — holds since 2026-05-27 — tap for who they are Same subject: Agentic coding capabilities have improved significantly and agents are becoming exponentially better at executing complex tasks. — tap to centre the map on it Agentic coding capabilities haveimproved significantly and agentsare becoming exponentially better atexecuting complex tasks. Last stated 3 weeks ago 2 Nov 2026 MB Matt Birchler — holds since 2026-11-02 — 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 alot of low-quality output thatdevelopers will need to clean up,even as it also produces goodresults. 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 correctyet be slightly wrong, which is whycode 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 treatedas untrusted until there is evidenceit 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: AI-generated code should not count as finished work until a human has reviewed and corrected it. — tap to centre the map on it AI-generated code should not countas finished work until a human hasreviewed and corrected it. Last stated 8 months ago 1 Apr 2026 DJ Daniel Jalkut — holds since 2026-04-01 — tap for who they are Same subject: As AI makes it easier to generate code, teams must delete code more aggressively or be overwhelmed by accumulated complexity. — tap to centre the map on it As AI makes it easier to generatecode, teams must delete code moreaggressively or be overwhelmed byaccumulated complexity. Last stated 3 months ago 1 Sept 2026 VB Vicki Boykis — holds since 2026-09-01 — tap for who they are Same subject: Code should be accepted based on its merit and accountability for it should be assigned. — tap to centre the map on it Code should be accepted based on itsmerit and accountability for itshould be assigned. Last stated 2 months ago 20 Sept 2026 TL Tobias Lütke — holds since 2026-09-20 — tap for who they are Same subject: Descriptive variable or function names are preferable to code comments that add nothing, which are slop. — tap to centre the map on it Descriptive variable or functionnames are preferable to codecomments that add nothing, which areslop. Last stated a year ago 25 Aug 2025 LR Lee Robinson — holds since 2025-08-25 — tap for who they are Same subject: Preventing agent-generated slop is a simple three-pronged process involving high quality PR creation, agentic PR review, and disaster recovery processes. — tap to centre the map on it Preventing agent-generated slop is asimple three-pronged processinvolving high quality PR creation,agentic PR review, and disasterrecovery processes. Last stated a month ago 13 Oct 2026 KD Kent C. Dodds — holds since 2026-10-13 — tap for who they are Same subject: Reviewing AI-written code means asking whether it does anything dangerous, touches only the expected files, is covered by tests and follows architecture convention, then only spot-checking the code itself. — tap to centre the map on it Reviewing AI-written code meansasking whether it does anythingdangerous, touches only the expectedfiles, is covered by tests andfollows architecture convention,then only spot-checking the codeitself. Last stated 3 months ago 5 Sept 2026 BV Ben Vinegar — holds since 2026-09-05 — 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 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 Read this korrent →