Tap a claim on the ring to put it at the centre.
← AI coding tools perform better on greenfield projects than on existing…
17 connected korrents · 16 moments from 8 Feb 2017 to 22 Sept 2026.
Everything filed under code generation
code generation
Everything filed under developer tools
developer tools
Everything filed under coding agents
coding agents
Everything filed under AI slop
AI slop
Everything filed under product management
product management
Everything filed under design
design
Everything filed under AI and jobs
AI and jobs 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: AI coding tools perform better on greenfield projects than on existing codebases, though the advantage is smaller than commonly assumed. AI coding tools perform better on greenfield projects than on existing codebases, though the advantage is smaller than commonly assumed. Last stated 8 months ago
22 Jan 2026
SK
Steve Klabnik — holds since 2026-01-22 — 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 coding tools change nothing except that engineers are happier, and for a lot of companies that is not good enough to keep paying for. Last stated 4 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — 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 a lot of low-quality output that developers will need to clean up, even as it also produces good results. Last stated 8 months ago
9 Feb 2026
SH
Scott Hanselman — holds since 2026-02-09 — tap for who they are
Same subject: Before product-market fit, coding faster does not help: it is better to think a lot than to swing a lot, and AI does not speed up the thinking. — tap to centre the map on it Before product-market fit, coding faster does not help: it is better to think a lot than to swing a lot, and AI does not speed up the thinking. Last stated 4 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: As AI makes code cheaper to produce, understanding and architectural design become more valuable. — tap to centre the map on it As AI makes code cheaper to produce, understanding and architectural design become more valuable. Last stated 2 years ago
27 Jan 2025
NE
Nelson Elhage — holds since 2025-01-27 — tap for who they are
Same subject: AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard. — tap to centre the map on it AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard. Last stated a year ago
30 Apr 2025
TS
Tim Sweeney — holds since 2025-04-30 — tap for who they are
Same subject: Effective use of AI coding tools requires domain expertise: the tool should be used as an assistant, not as a replacement for the engineer. — tap to centre the map on it Effective use of AI coding tools requires domain expertise: the tool should be used as an assistant, not as a replacement for the engineer. Last stated 12 months ago
11 Oct 2025
MH
Mitchell Hashimoto — holds since 2025-10-11 — tap for who they are
Same subject: AI will not replace the best programmers; it will make them ten times more productive than they are today. — tap to centre the map on it AI will not replace the best programmers; it will make them ten times more productive than they are today. Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: AI has already made sweeping mechanical changes cheap; the unsolved problem is getting the same productivity when adding features to an old, entangled codebase. — tap to centre the map on it AI has already made sweeping mechanical changes cheap; the unsolved problem is getting the same productivity when adding features to an old, entangled codebase. Last stated 6 months ago
1 Apr 2026
TP
Thuan Pham — holds since 2026-04-01 — 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 a month ago
31 Aug 2026
CH
Craig Hockenberry — holds since 2026-08-31 — tap for who they are
Same subject: Automated evaluation tools are useful for finding some types of AI errors, especially when combined with human judgment. — tap to centre the map on it Automated evaluation tools are useful for finding some types of AI errors, especially when combined with human judgment. Last stated a week ago
22 Sept 2026
LR
Lenny Rachitsky — holds since 2026-09-22 — tap for who they are
Same subject: CMake tooling is missing a linter that could statically catch most CMakeLists.txt mistakes. — tap to centre the map on it CMake tooling is missing a linter that could statically catch most CMakeLists.txt mistakes. Last stated 2 weeks ago
20 Sept 2026
CW
Chris Wellons — holds since 2026-09-20 — tap for who they are
Same subject: Comparing code coverage between passing and failing test runs is a cheap, effective way to localize a bug quickly. — tap to centre the map on it Comparing code coverage between passing and failing test runs is a cheap, effective way to localize a bug quickly. Last stated a year ago
25 Apr 2025
RC
Russ Cox — holds since 2025-04-25 — tap for who they are
Same subject: Building powerful developer tools such as compilers, interpreters, and query languages requires knowledge of parsing. — tap to centre the map on it Building powerful developer tools such as compilers, interpreters, and query languages requires knowledge of parsing. Last stated 10 years ago
8 Feb 2017
TB
Thorsten Ball — holds since 2017-02-08 — tap for who they are
Same subject: In every developer-tool category — databases, compilers, whatever — the open source option eventually becomes the default option. — tap to centre the map on it In every developer-tool category — databases, compilers, whatever — the open source option eventually becomes the default option. Last stated 4 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: Most macros just transform their arguments, so running them during static analysis is usually safe even though it can't be guaranteed. — tap to centre the map on it Most macros just transform their arguments, so running them during static analysis is usually safe even though it can't be guaranteed. Last stated 3 years ago
31 Dec 2023
PH
Phil Hagelberg — holds since 2023-12-31 — tap for who they are
At the centre
AI coding tools perform better on greenfield projects than on existing codebases, though the advantage is smaller than commonly assumed.
Holds Read this korrent →
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.
Holds
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.
Holds
Before product-market fit, coding faster does not help: it is better to think a lot than to swing a lot, and AI does not speed up the thinking.
Holds
As AI makes code cheaper to produce, understanding and architectural design become more valuable.
Holds
AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard.
Holds
Effective use of AI coding tools requires domain expertise: the tool should be used as an assistant, not as a replacement for the engineer.
Holds
AI will not replace the best programmers; it will make them ten times more productive than they are today.
Holds
AI has already made sweeping mechanical changes cheap; the unsolved problem is getting the same productivity when adding features to an old, entangled codebase.
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
Automated evaluation tools are useful for finding some types of AI errors, especially when combined with human judgment.
Holds
CMake tooling is missing a linter that could statically catch most CMakeLists.txt mistakes.
Holds
Comparing code coverage between passing and failing test runs is a cheap, effective way to localize a bug quickly.
Holds
Building powerful developer tools such as compilers, interpreters, and query languages requires knowledge of parsing.
Holds
In every developer-tool category — databases, compilers, whatever — the open source option eventually becomes the default option.
Holds
Most macros just transform their arguments, so running them during static analysis is usually safe even though it can't be guaranteed.
Holds