Tap a claim on the ring to put it at the centre.
← Clearing an agent's session is now often a disadvantage, because the…
17 connected korrents · 16 moments from 19 Jun 2024 to 24 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under AI agents
AI agents
Everything filed under LLMs
LLMs 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: Clearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does. 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 2 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. — tap to centre the map on it An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. Last stated 7 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Decoupling an agent's components improves security and auditability. — tap to centre the map on it Decoupling an agent's components improves security and auditability. Last stated 4 weeks ago
23 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-23 — tap for who they are
Same subject: The advantage of digital minds may be the opposite of pooling knowledge: deliberately giving agents different contexts, which is a control humans do not have over themselves. — tap to centre the map on it The advantage of digital minds may be the opposite of pooling knowledge: deliberately giving agents different contexts, which is a control humans do not have over themselves. Last stated 4 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: The binding constraint on agent work is machines, not models: a cloud session is easy for web work and almost every tool fails the moment the job needs macOS. — tap to centre the map on it The binding constraint on agent work is machines, not models: a cloud session is easy for web work and almost every tool fails the moment the job needs macOS. Last stated 2 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — 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 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — 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 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Working alone with agents may be efficient, but it means people stop learning from each other. — tap to centre the map on it Working alone with agents may be efficient, but it means people stop learning from each other. Last stated a month ago
10 Sept 2026
KS
Karri Saarinen — holds since 2026-09-10 — tap for who they are
Same subject: Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions. — tap to centre the map on it Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions. Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — tap for who they are
Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — 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 7 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 developer using AI coding tools remains responsible for reviewing the code they ship. — tap to centre the map on it A developer using AI coding tools remains responsible for reviewing the code they ship. Last stated 7 months ago
10 Mar 2026
JS
Jon Seager — holds since 2026-03-10 — tap for who they are
Same subject: A software engineer who is not using a tool like Cursor is working at half productivity or worse. — tap to centre the map on it A software engineer who is not using a tool like Cursor is working at half productivity or worse. Last stated a year ago
18 Aug 2025
BT
Bret Taylor — holds since 2025-08-18 — tap for who they are
Same subject: AI coding assistants remove repetitive work without replacing human judgment. — tap to centre the map on it AI coding assistants remove repetitive work without replacing human judgment. Last stated 8 months ago
17 Feb 2026
EB
Emanuele Bartolesi — holds since 2026-02-17 — tap for who they are
Same subject: Anthropic pulling Claude subscriptions from third-party harnesses like OpenCode is a mistake: playing a single match in a game of many rounds. — tap to centre the map on it Anthropic pulling Claude subscriptions from third-party harnesses like OpenCode is a mistake: playing a single match in a game of many rounds. Last stated 7 months ago
8 Apr 2026
DH
David Heinemeier Hansson — holds since 2026-04-08 — tap for who they are
Same subject: Claude Code will eventually build persistent, failure-tolerant iteration into its default operating loop. — tap to centre the map on it Claude Code will eventually build persistent, failure-tolerant iteration into its default operating loop. Last stated 9 months ago
6 Feb 2026
AK
Arvid Kahl — holds since 2026-02-06 — tap for who they are
Same subject: Claude's hack of adding everything to git and then diffing it is definitely an option but very heavy-handed. — tap to centre the map on it Claude's hack of adding everything to git and then diffing it is definitely an option but very heavy-handed. Last stated 4 weeks ago
24 Sept 2026
AR
Armin Ronacher — holds since 2026-09-24 — tap for who they are
At the centre
Clearing an agent's session is now often a disadvantage, because the accumulated context helps the model more than a clean start does.
Holds Read this korrent →
An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job.
Holds
Decoupling an agent's components improves security and auditability.
Holds
The advantage of digital minds may be the opposite of pooling knowledge: deliberately giving agents different contexts, which is a control humans do not have over themselves.
Holds
The binding constraint on agent work is machines, not models: a cloud session is easy for web work and almost every tool fails the moment the job needs macOS.
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
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
Working alone with agents may be efficient, but it means people stop learning from each other.
Holds
Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions.
Holds
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
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 developer using AI coding tools remains responsible for reviewing the code they ship.
Holds
A software engineer who is not using a tool like Cursor is working at half productivity or worse.
Holds
AI coding assistants remove repetitive work without replacing human judgment.
Holds
Anthropic pulling Claude subscriptions from third-party harnesses like OpenCode is a mistake: playing a single match in a game of many rounds.
Holds
Claude Code will eventually build persistent, failure-tolerant iteration into its default operating loop.
Holds
Claude's hack of adding everything to git and then diffing it is definitely an option but very heavy-handed.
Holds