korrents

On the map

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

← Code-style constraints for AI coding agents, such as function-length…

17 connected korrents · 17 moments from 28 Apr 2023 to 14 Oct 2026. Nearly all of them are about coding agents.

Everything filed under LLMs LLMs Everything filed under AI agents AI agents Everything filed under humility humility Everything filed under open source open source Everything filed under solar solar Everything filed under design design Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Code-style constraints for AI coding agents, such as function-length limits, are more reliably enforced as automated lints than by hoping the agent internalizes preferences. Code-style constraints for AI codingagents, such as function-length limits,are more reliably enforced as automatedlints than by hoping the agentinternalizes preferences. Last stated 8 months ago 10 Mar 2026 JS Jon Seager — holds since 2026-03-10 — tap for who they are Same subject: A common mistake is asking coding agents to change code the developer does not yet understand. — tap to centre the map on it A common mistake is asking codingagents to change code the developerdoes not yet understand. Last stated 7 months ago 15 Apr 2026 LR Lee Robinson — holds since 2026-04-15 — tap for who they are Same subject: AI coding agents advance open source's founding goal by letting far more people modify software, so barring AI-assisted contributions protects a guild rather than the mission. — tap to centre the map on it AI coding agents advance opensource's founding goal by lettingfar more people modify software, sobarring AI-assisted contributionsprotects a guild rather than themission. Last stated 6 months ago 1 Jun 2026 DH David Heinemeier Hansson — holds since 2026-06-01 — tap for who they are Same subject: AI coding agents have made redesigning existing systems cheap enough that developers actually redesign instead of living with a flawed design. — tap to centre the map on it AI coding agents have maderedesigning existing systems cheapenough that developers actuallyredesign instead of living with aflawed design. Last stated 8 months ago 16 Mar 2026 KD Kent C. Dodds — holds since 2026-03-16 — tap for who they are Same subject: AI coding agents pulling unknown code onto corporate networks will be exploited, and it will take the shape of a supply-chain attack. — tap to centre the map on it AI coding agents pulling unknowncode onto corporate networks will beexploited, and it will take theshape of a supply-chain attack. Last stated 3 months ago 4 Sept 2026 BS Bruce Schneier — holds since 2026-09-04 — tap for who they are Same subject: AI coding agents work best with the same general-purpose tools built for humans, such as git and file utilities, rather than agent-specific interfaces. — tap to centre the map on it AI coding agents work best with thesame general-purpose tools built forhumans, such as git and fileutilities, rather thanagent-specific interfaces. Last stated a year ago 30 Sept 2025 HR Harper Reed — holds since 2025-09-30 — tap for who they are Same subject: As a small design team, you should not stand in the way of engineers designing with coding agents but find ways to support them. — tap to centre the map on it As a small design team, you shouldnot stand in the way of engineersdesigning with coding agents butfind ways to support them. Last stated 2 months ago 15 Sept 2026 NF Nev Flynn — holds since 2026-09-15 — tap for who they are Same subject: As coding agents improve, the main failure is not broken code but code that violates a system’s implicit contract. — tap to centre the map on it As coding agents improve, the mainfailure is not broken code but codethat violates a system’s implicitcontract. Last stated 10 months ago 3 Feb 2026 SG Sarah Guo — holds since 2026-02-03 — 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: Code quality still matters even as LLMs make writing code much faster — tap to centre the map on it Code quality still matters even asLLMs make writing code much faster Last stated 2 years ago 13 May 2025 DH David Heinemeier Hansson — holds since 2025-05-13 — 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 asLLMs 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: Current AIs are universal personal interns whose work must be checked and improved before release. — tap to centre the map on it Current AIs are universal personalinterns whose work must be checkedand improved before release. Last stated 4 years ago 28 Apr 2023 KK Kevin Kelly — holds since 2023-04-28 — tap for who they are Same subject: Evals are just testing: a way to test LLM outputs the way unit tests test software. — tap to centre the map on it Evals are just testing: a way totest LLM outputs the way unit teststest software. Last stated 2 years ago 18 Mar 2025 JM John Maeda — holds since 2025-03-18 — tap for who they are Same subject: Large AI-made replacements of big applications tend not to work very well, from what has been seen so far. — tap to centre the map on it Large AI-made replacements of bigapplications tend not to work verywell, from what has been seen sofar. Last stated a month ago 14 Oct 2026 DP Dave Plummer — holds since 2026-10-14 — tap for who they are Same subject: LLM-driven automatic QA can raise software release quality and offset quality lost to faster AI-generated code. — tap to centre the map on it LLM-driven automatic QA can raisesoftware release quality and offsetquality lost to faster AI-generatedcode. Last stated 6 months ago 7 Jun 2026 SS Salvatore Sanfilippo — holds since 2026-06-07 — tap for who they are Same subject: A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first. — tap to centre the map on it A strength of Claude is that it isgood at ranking your options, lowestrisk and least expensive first. Last stated 5 months ago 16 Jun 2026 BW Brett Williams — holds since 2026-06-16 — tap for who they are Same subject: Among the misuse threats in Anthropic's threat disruption report, distillation is by far the most important and will have the most impact. — tap to centre the map on it Among the misuse threats inAnthropic's threat disruptionreport, distillation is by far themost important and will have themost impact. Last stated 2 months ago 15 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-15 — tap for who they are Same subject: Anthropic prices its Claude subscription plans as loss leaders relative to its own API rates. — tap to centre the map on it Anthropic prices its Claudesubscription plans as loss leadersrelative to its own API rates. Last stated 2 months ago 19 Sept 2026 BD Brad DeLong — holds since 2026-09-19 — 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 Code-style constraints for AI coding agents, such as function-length limits, are more reliably enforced as automated lints than by hoping the agent internalizes preferences. Last stated 10 Mar 2026 · 8 months ago Holds Jon Seager Read this korrent →