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 · 15 moments from 18 Mar 2024 to 21 Oct 2026.
Everything filed under Anthropic
Anthropic
Everything filed under vibe coding
vibe coding
Everything filed under OpenAI
OpenAI
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs
Everything filed under code generation
code generation 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 7 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: Judging one model worse than another from a one-shot, probabilistic output on a given day is not a good way to evaluate it. — tap to centre the map on it Judging one model worse than another from a one-shot, probabilistic output on a given day is not a good way to evaluate it. Last stated 5 months ago
19 May 2026
TG
Tommy Geoco — holds since 2026-05-19 — tap for who they are
Same subject: Claude Opus 5.5 is a Tier 2 cyber model, despite Anthropic placing it in the lower category. — tap to centre the map on it Claude Opus 5.5 is a Tier 2 cyber model, despite Anthropic placing it in the lower category. Last stated 4 weeks ago
23 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-23 — 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 that nobody has worked out yet. Last stated 7 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 wrote it, and it will tell you the code is great. Last stated 3 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 why, and no way to fix it when it breaks. Last stated 3 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 struggled to understand the domain yourself. Last stated 4 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 uncannily close to what its user would have written themselves. Last stated 2 months ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt. — tap to centre the map on it A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt. Last stated 4 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — tap for who they are
Same subject: A boring but non-superficial SaaS app that would have done well five years ago might now get no signups because tens of thousands can easily vibe code it. — tap to centre the map on it A boring but non-superficial SaaS app that would have done well five years ago might now get no signups because tens of thousands can easily vibe code it. Last stated 2 months ago
1 Sept 2026
PL
Pieter Levels — holds since 2026-09-01 — tap for who they are
Same subject: A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. — tap to centre the map on it A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. Last stated 7 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A screenshot is the fastest, easiest way to build, without having to voice it or type it. — tap to centre the map on it A screenshot is the fastest, easiest way to build, without having to voice it or type it. Last stated 4 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — tap for who they are
Same subject: A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. Last stated yesterday
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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 suggests. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: AI makes it easier to hack things together, but this is not engineering. — tap to centre the map on it AI makes it easier to hack things together, but this is not engineering. Last stated 4 weeks ago
26 Sept 2026
GO
Gergely Orosz — holds since 2026-09-26 — tap for who they are
Same subject: AI tools are now highly effective at generating UI code from a rough natural-language description — tap to centre the map on it AI tools are now highly effective at generating UI code from a rough natural-language description Last stated 7 months ago
7 Apr 2026
CW
Chris Wellons — holds since 2026-04-07 — tap for who they are
Same subject: If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced. — tap to centre the map on it If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced. Last stated 2 months ago
12 Aug 2026
CM
Charity Majors — holds since 2026-08-12 — 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 →
Judging one model worse than another from a one-shot, probabilistic output on a given day is not a good way to evaluate it.
Holds
Claude Opus 5.5 is a Tier 2 cyber model, despite Anthropic placing it in the lower category.
Holds
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
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
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
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
A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt.
Holds
A boring but non-superficial SaaS app that would have done well five years ago might now get no signups because tens of thousands can easily vibe code it.
Holds
A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break.
Holds
A screenshot is the fastest, easiest way to build, without having to voice it or type it.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
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
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
Holds
AI makes it easier to hack things together, but this is not engineering.
Holds
AI tools are now highly effective at generating UI code from a rough natural-language description
Holds
If you are not going to read the generated code, what you need is conformance testing: proof that it performs within the boundaries of the code it replaced.
Holds