Tap a claim on the ring to put it at the centre.
← Trusting model-written code you have not read became defensible only…
17 connected korrents · 13 moments on record from 18 Mar 2024 to 3 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under OpenAI
OpenAI
Everything filed under software quality
software quality
Everything filed under Anthropic
Anthropic
Everything filed under vibe coding
vibe coding
Everything filed under Microsoft
Microsoft 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: Trusting model-written code you have not read became defensible only with Opus 4.5, and only for classes of problem you have already watched a model handle. Trusting model-written code you have not read became defensible only with Opus 4.5, and only for classes of problem you have already watched a model handle. Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: The interesting question is not what the next model will be able to do, but what the models already released can do that nobody has worked out yet. — tap to centre the map on it The interesting question is not what the next model will be able to do, but what the models already released can do… Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great. — tap to centre the map on it Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. — tap to centre the map on it The code today’s models and agents write is very hard to follow: you get better performance without knowing… Last stated 2 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — tap for who they are
Same subject: The industry is now accumulating code faster than it is accumulating trust, and trust only comes from having struggled to understand the domain yourself. — tap to centre the map on it The industry is now accumulating code faster than it is accumulating trust, and trust only comes from having… Last stated 2 months ago
1 Jul 2026
KB
Kent Beck — holds since 2026-07-01 — tap for who they are
Same subject: The release of Opus 4.5 in November 2025 was the dividing line, because it was the first time an agent produced work uncannily close to what its user would have written themselves. — tap to centre the map on it The release of Opus 4.5 in November 2025 was the dividing line, because it was the first time an agent produced work… Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: The incident in which a model escaped its sandbox was an alignment failure and a security failure at once, and OpenAI made big mistakes in it. — tap to centre the map on it The incident in which a model escaped its sandbox was an alignment failure and a security failure at once, and… Last stated a month ago
28 Jul 2026
SA
Sam Altman — holds since 2026-07-28 — tap for who they are
Same subject: A sense of achievement in software survives writing almost none of the code yourself. — tap to centre the map on it A sense of achievement in software survives writing almost none of the code yourself. Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models. — tap to centre the map on it A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people… Last stated 6 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the whole instruction becomes: write code until these tests pass. — tap to centre the map on it A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the… Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would. — tap to centre the map on it A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and… Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is infinitely harder to evolve software that has users. — tap to centre the map on it Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is… Last stated 4 weeks ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. — tap to centre the map on it A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless… Last stated 5 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on. — tap to centre the map on it A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on. Last stated 4 days ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its tasks are so legible and verifiable. — tap to centre the map on it A machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its… Last stated 3 weeks ago
14 Aug 2026
SP
Sunil Pai — holds since 2026-08-14 — tap for who they are
Same subject: A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history… Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. — tap to centre the map on it A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both… Last stated 4 days ago
3 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-03 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently… Last stated 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
At the centre
Trusting model-written code you have not read became defensible only with Opus 4.5, and only for classes of problem you have already watched a model handle.
Holds Read this korrent →
The interesting question is not what the next model will be able to do, but what the models already released can do that nobody has worked out yet.
Holds
Agentic code review raises the floor but cannot be trusted, because the model reading the code is the same model that wrote it, and it will tell you the code is great.
Holds DH Dex Horthy
The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks.
Holds ES Elizabeth Stone
The industry is now accumulating code faster than it is accumulating trust, and trust only comes from having struggled to understand the domain yourself.
Holds KB Kent Beck
The release of Opus 4.5 in November 2025 was the dividing line, because it was the first time an agent produced work uncannily close to what its user would have written themselves.
Holds
The incident in which a model escaped its sandbox was an alignment failure and a security failure at once, and OpenAI made big mistakes in it.
Holds
A sense of achievement in software survives writing almost none of the code yourself.
Holds
A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models.
Holds SY Steve Yegge
A language-agnostic conformance suite is the most powerful thing you can hand a coding agent, because the whole instruction becomes: write code until these tests pass.
Holds
A passing test suite is not evidence that the software works, so an agent must also be made to start the thing and exercise it the way a person would.
Holds
Adding a config option so nobody breaks compounds into permutations no test suite can cover, because it is infinitely harder to evolve software that has users.
Holds
A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
Holds
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.
Holds
A machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its tasks are so legible and verifiable.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it.
Holds ZM Zvi Mowshowitz
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds