Tap a claim on the ring to put it at the centre.
← A coding agent does not learn from its mistakes the way a person does…
17 connected korrents · 15 moments on record from 3 Feb 2025 to 3 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under Anthropic
Anthropic
Everything filed under recursive self-improvement
recursive self-improvement
Everything filed under MCP
MCP In tension 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: 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. 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 5 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
In tension: Agent-written pull requests already outclass those of the median human contributor to an open source project. — tap to centre the map on it Agent-written pull requests already outclass those of the median human contributor to an open source project. Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: Working with coding agents is a skill you learn like an instrument; judging the tools after one try is like calling a piano bad after one go. — tap to centre the map on it Working with coding agents is a skill you learn like an instrument; judging the tools after one try is like calling… Last stated 7 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get. — tap to centre the map on it Long-running agents fail because they drift off the distribution they were trained on, and degrade further the… Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Working with a coding agent should leave both of you better every day, and that only happens if you deliberately record what was learned and decided in the session. — tap to centre the map on it Working with a coding agent should leave both of you better every day, and that only happens if you… Last stated 3 weeks ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: Overly prescriptive instructions make a coding agent worse, for the same reason a micromanaging boss makes a programmer worse. — tap to centre the map on it Overly prescriptive instructions make a coding agent worse, for the same reason a micromanaging boss… Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — 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… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The part of a coding agent that actually acts on code is not AI at all — it is simple systems code wired to ground truth, the way a Makefile is. — tap to centre the map on it The part of a coding agent that actually acts on code is not AI at all — it is simple systems code wired to ground… Last stated a year ago
2 Jun 2025
TP
Thomas Ptacek — holds since 2025-06-02 — tap for who they are
Same subject: Being an excellent programmer is a burden rather than an advantage when learning to work with coding agents. — tap to centre the map on it Being an excellent programmer is a burden rather than an advantage when learning to work with coding agents. Last stated 7 months ago
12 Feb 2026
LF
Lex Fridman — holds since 2026-02-12 — tap for who they are
Same subject: What limits you with coding agents is your own skill at stringing them together, not the capability of the models. — tap to centre the map on it What limits you with coding agents is your own skill at stringing them together, not the capability of the models. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — 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… Last stated 4 days ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces. — tap to centre the map on it A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it… Last stated 5 days ago
2 Sept 2026
SW
Simon Willison — holds since 2026-09-02 — 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… Last stated 4 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — tap for who they are
Same subject: AI takeover is not the thing to worry about: physical constraints bound recursive self-improvement, and humans reliably act once a risk becomes immediate. — tap to centre the map on it AI takeover is not the thing to worry about: physical constraints bound recursive self-improvement, and humans… Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: Coding is not just another application domain for AI; it is the meta-skill that lets AI generate its own training material and start the recursive self-improvement loop. — tap to centre the map on it Coding is not just another application domain for AI; it is the meta-skill that lets AI generate its own training… Last stated 4 weeks ago
10 Aug 2026
FC
François Chollet — holds since 2026-08-10 — tap for who they are
Same subject: Recursive self-improvement has already started, because AI research itself is now being automated. — tap to centre the map on it Recursive self-improvement has already started, because AI research itself is now being automated. Last stated 7 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context. — tap to centre the map on it Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP… Last stated 7 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: MCP is not a new foundation for anything — it is API design, and Kubernetes was already turning one intention into seven calls a decade ago. — tap to centre the map on it MCP is not a new foundation for anything — it is API design, and Kubernetes was already turning one intention… Last stated 3 months ago
3 Jun 2026
KH
Kelsey Hightower — holds since 2026-06-03 — tap for who they are
At the centre
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 Read this korrent →
Agent-written pull requests already outclass those of the median human contributor to an open source project.
Holds
Working with coding agents is a skill you learn like an instrument; judging the tools after one try is like calling a piano bad after one go.
Holds
Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get.
Holds JD Jeff Dean
Working with a coding agent should leave both of you better every day, and that only happens if you deliberately record what was learned and decided in the session.
Holds AO Addy Osmani
Overly prescriptive instructions make a coding agent worse, for the same reason a micromanaging boss makes a programmer worse.
Holds
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 DH Dex Horthy
The part of a coding agent that actually acts on code is not AI at all — it is simple systems code wired to ground truth, the way a Makefile is.
Holds
Being an excellent programmer is a burden rather than an advantage when learning to work with coding agents.
Holds LF Lex Fridman
What limits you with coding agents is your own skill at stringing them together, not the capability of the models.
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 language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces.
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 ER Eric Ries
AI takeover is not the thing to worry about: physical constraints bound recursive self-improvement, and humans reliably act once a risk becomes immediate.
Holds NL Nathan Lambert
Coding is not just another application domain for AI; it is the meta-skill that lets AI generate its own training material and start the recursive self-improvement loop.
Holds
Recursive self-improvement has already started, because AI research itself is now being automated.
Holds JL Jan Leike
Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context.
Holds
MCP is not a new foundation for anything — it is API design, and Kubernetes was already turning one intention into seven calls a decade ago.
Holds KH Kelsey Hightower