Tap a claim on the ring to put it at the centre.
← The step change in AI coding in 2025 came from the harnesses and the…
17 connected korrents · 16 moments from 16 Dec 2024 to 24 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under Anthropic
Anthropic
Everything filed under LLMs
LLMs
Everything filed under developer tools
developer tools
Everything filed under software quality
software quality 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: The step change in AI coding in 2025 came from the harnesses and the tooling around the models, not from the models themselves. The step change in AI coding in 2025 came from the harnesses and the tooling around the models, not from the models themselves. Last stated 2 months ago
12 Aug 2026
CM
Charity Majors — holds since 2026-08-12 — tap for who they are
Same subject: Capabilities provided by harnesses around AI models are increasingly shifting into the model itself. — tap to centre the map on it Capabilities provided by harnesses around AI models are increasingly shifting into the model itself. Last stated 2 months ago
3 Sept 2026
FC
François Chollet — holds since 2026-09-03 — tap for who they are
Same subject: The next big leap for AI models probably isn't likely until they are exposed to proprietary corporate code — tap to centre the map on it The next big leap for AI models probably isn't likely until they are exposed to proprietary corporate code Last stated 2 years ago
16 Dec 2024
DH
David Heinemeier Hansson — holds since 2024-12-16 — tap for who they are
Same subject: AI has changed software development enough that some old assumptions about it no longer hold. — tap to centre the map on it AI has changed software development enough that some old assumptions about it no longer hold. Last stated 9 months ago
15 Jan 2026
SK
Steve Klabnik — holds since 2026-01-15 — tap for who they are
Same subject: The AI coding tools only recently became good enough to change the answer: after years of hating them, most of this codebase is now written by AI. — tap to centre the map on it The AI coding tools only recently became good enough to change the answer: after years of hating them, most of this codebase is now written by AI. Last stated 4 months ago
24 Jun 2026
NE
NeetCode — holds since 2026-06-24 — tap for who they are
Same subject: The prediction that 90% of code will be AI-written by the end of 2025 deserves skepticism, though manual programming may yet become a horse: ridden for love, not transport. — tap to centre the map on it The prediction that 90% of code will be AI-written by the end of 2025 deserves skepticism, though manual programming may yet become a horse: ridden for love, not transport. Last stated a year ago
12 Jul 2025
DH
David Heinemeier Hansson — holds since 2025-07-12 — tap for who they are
Same subject: Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. — tap to centre the map on it Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. Last stated a year ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: AI models are now much more than text-to-code converters. — tap to centre the map on it AI models are now much more than text-to-code converters. Last stated 4 weeks ago
24 Sept 2026
TB
Thorsten Ball — holds since 2026-09-24 — tap for who they are
Same subject: AI marketed as a pure augmenting 'tool' will end up automating jobs anyway, since firms control how it's used. — tap to centre the map on it AI marketed as a pure augmenting 'tool' will end up automating jobs anyway, since firms control how it's used. Last stated 5 months ago
13 May 2026
JS
Jasmine Sun — holds since 2026-05-13 — 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: 95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away. — tap to centre the map on it 95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away. Last stated 4 weeks ago
23 Sept 2026
GT
Geoff Teehan — holds since 2026-09-23 — tap for who they are
Same subject: A feature added to a codebase is extremely difficult to remove once other code is built on top of it. — tap to centre the map on it A feature added to a codebase is extremely difficult to remove once other code is built on top of it. Last stated 2 months ago
1 Sept 2026
VB
Vicki Boykis — holds since 2026-09-01 — tap for who they are
Same subject: A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. — tap to centre the map on it A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. Last stated a month ago
14 Sept 2026
JS
Jason Snell — holds since 2026-09-14 — tap for who they are
At the centre
The step change in AI coding in 2025 came from the harnesses and the tooling around the models, not from the models themselves.
Holds Read this korrent →
Capabilities provided by harnesses around AI models are increasingly shifting into the model itself.
Holds
The next big leap for AI models probably isn't likely until they are exposed to proprietary corporate code
Holds
AI has changed software development enough that some old assumptions about it no longer hold.
Holds
The AI coding tools only recently became good enough to change the answer: after years of hating them, most of this codebase is now written by AI.
Holds
The prediction that 90% of code will be AI-written by the end of 2025 deserves skepticism, though manual programming may yet become a horse: ridden for love, not transport.
Holds
Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before.
Holds
AI models are now much more than text-to-code converters.
Holds
AI marketed as a pure augmenting 'tool' will end up automating jobs anyway, since firms control how it's used.
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
95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away.
Holds
A feature added to a codebase is extremely difficult to remove once other code is built on top of it.
Holds
A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta.
Holds