Tap a claim on the ring to put it at the centre.
← The quality of the context given to an AI matters more than the model's inherent capability.
17 connected korrents · 15 moments on record from 30 Jun 2022 to 14 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs
Everything filed under software quality
software quality
Everything filed under Anthropic
Anthropic 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 quality of the context given to an AI matters more than the model's inherent capability. The quality of the context given to an AI matters more than the model's inherent capability. Last stated 2 months ago
9 Jul 2026
TF
Tiago Forte — holds since 2026-07-09 — tap for who they are
Same subject: When an AI writes bad code the thing to fix is the context it was given, not the code, because fixing the output adds no leverage. — tap to centre the map on it When an AI writes bad code the thing to fix is the context it was given, not the code, because fixing the output adds no leverage. Last stated a year ago
18 Aug 2025
BT
Bret Taylor — holds since 2025-08-18 — tap for who they are
Same subject: The surrounding system framework and scaffolding matter more for AI agent capability than the underlying model. — tap to centre the map on it The surrounding system framework and scaffolding matter more for AI agent capability than the underlying model. Last stated 3 months ago
21 Jun 2026
EY
Eugene Yan — holds since 2026-06-21 — tap for who they are
Same subject: People disagreeing about AI capability are speaking past each other, because they are using models of very different tiers on very different kinds of task. — tap to centre the map on it People disagreeing about AI capability are speaking past each other, because they are using models of very different tiers on very different kinds of task. Last stated 5 months ago
9 Apr 2026
AK
Andrej Karpathy — holds since 2026-04-09 — tap for who they are
Same subject: The best-performing AI model in a category earns outsized pricing power over models that are merely close to it. — tap to centre the map on it The best-performing AI model in a category earns outsized pricing power over models that are merely close to it. Last stated a week ago
14 Sept 2026
BH
Byrne Hobart — holds since 2026-09-14 — tap for who they are
Same subject: Current AI models still fall short of expert human performance. — tap to centre the map on it Current AI models still fall short of expert human performance. Last stated 2 years ago
27 Jan 2025
NE
Nelson Elhage — holds since 2025-01-27 — tap for who they are
Same subject: The deployment layer surrounding a model is as important as the model's raw intelligence. — tap to centre the map on it The deployment layer surrounding a model is as important as the model's raw intelligence. Last stated 3 months ago
4 Jul 2026
LW
Lilian Weng — holds since 2026-07-04 — tap for who they are
Same subject: What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. — tap to centre the map on it What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. Last stated 2 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Most of the value an AI expert brings to a company is telling it not to use AI. — tap to centre the map on it Most of the value an AI expert brings to a company is telling it not to use AI. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — 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 a human notices and writes it down. Last stated 6 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. — tap to centre the map on it A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. Last stated a year ago
18 Aug 2025
CB
Clay Bavor — holds since 2025-08-18 — 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 3 weeks ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — 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 3 weeks ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A trust that owns the mission protects a company better than founder control does, which is why Anthropic needs no dual-class shares. — tap to centre the map on it A trust that owns the mission protects a company better than founder control does, which is why Anthropic needs no dual-class shares. Last stated 4 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — tap for who they are
Same subject: Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million. — tap to centre the map on it Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million. 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 whole instruction becomes: write code until these tests pass. 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 exercise it the way a person would. Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: A permanently painful on-call rotation is a five-alarm emergency, not a normal cost of owning code in production. — tap to centre the map on it A permanently painful on-call rotation is a five-alarm emergency, not a normal cost of owning code in production. Last stated 4 years ago
30 Jun 2022
CM
Charity Majors — holds since 2022-06-30 — tap for who they are
At the centre
The quality of the context given to an AI matters more than the model's inherent capability.
Holds Read this korrent →
When an AI writes bad code the thing to fix is the context it was given, not the code, because fixing the output adds no leverage.
Holds
The surrounding system framework and scaffolding matter more for AI agent capability than the underlying model.
Holds
People disagreeing about AI capability are speaking past each other, because they are using models of very different tiers on very different kinds of task.
Holds
The best-performing AI model in a category earns outsized pricing power over models that are merely close to it.
Holds
Current AI models still fall short of expert human performance.
Holds
The deployment layer surrounding a model is as important as the model's raw intelligence.
Holds
What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters.
Holds
Most of the value an AI expert brings to a company is telling it not to use AI.
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 left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair.
Holds
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.
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 trust that owns the mission protects a company better than founder control does, which is why Anthropic needs no dual-class shares.
Holds
Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million.
Holds
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
A permanently painful on-call rotation is a five-alarm emergency, not a normal cost of owning code in production.
Holds