Tap a claim on the ring to put it at the centre.
← Changes to an agent's project instructions should be driven by the…
17 connected korrents · 16 moments from 18 Mar 2024 to 21 Oct 2026.
Everything filed under coding agents
coding agents
Everything filed under Anthropic
Anthropic
Everything filed under OpenAI
OpenAI
Everything filed under scaling laws
scaling laws
Everything filed under product management
product management
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment 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: Changes to an agent's project instructions should be driven by the agents' session logs, not by what the author remembers being annoyed by. Changes to an agent's project instructions should be driven by the agents' session logs, not by what the author remembers being annoyed by. Last stated 2 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — tap for who they are
Same subject: An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. — tap to centre the map on it An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. Last stated 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Product managers should build an agent to write their weekly reports instead of writing them by hand. — tap to centre the map on it Product managers should build an agent to write their weekly reports instead of writing them by hand. Last stated 2 months ago
10 Sept 2026
TY
Tamar Yehoshua — holds since 2026-09-10 — tap for who they are
Same subject: Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore. — tap to centre the map on it Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore. Last stated 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The failure to identify codebase problems was a prompting problem. — tap to centre the map on it The failure to identify codebase problems was a prompting problem. Last stated 2 weeks ago
20 Oct 2026
KD
Kent C. Dodds — holds since 2026-10-20 — tap for who they are
Same subject: A maintainer no longer needs to read every pull request; agents can sort the chaff and leave only the decisions worth a human. — tap to centre the map on it A maintainer no longer needs to read every pull request; agents can sort the chaff and leave only the decisions worth a human. Last stated 2 months ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: Clearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does. — tap to centre the map on it Clearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does. Last stated 3 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: Loss-of-control accidents with AI have stopped being theoretical: one has now happened, and the goalposts moved rather than the risk receding. — tap to centre the map on it Loss-of-control accidents with AI have stopped being theoretical: one has now happened, and the goalposts moved rather than the risk receding. Last stated 3 months ago
28 Jul 2026
SA
Sam Altman — holds since 2026-07-28 — tap for who they are
Same subject: The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more. — tap to centre the map on it The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more. Last stated 5 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — 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: 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 2 weeks ago
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: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. Last stated 11 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. — tap to centre the map on it A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. Last stated 8 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
At the centre
Changes to an agent's project instructions should be driven by the agents' session logs, not by what the author remembers being annoyed by.
Holds Read this korrent →
An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation.
Holds
Product managers should build an agent to write their weekly reports instead of writing them by hand.
Holds
Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore.
Holds
The failure to identify codebase problems was a prompting problem.
Holds
A maintainer no longer needs to read every pull request; agents can sort the chaff and leave only the decisions worth a human.
Holds
Clearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does.
Holds
Loss-of-control accidents with AI have stopped being theoretical: one has now happened, and the goalposts moved rather than the risk receding.
Holds
The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more.
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
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
"Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next.
Holds
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Holds
A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from.
Holds