Tap a claim on the ring to put it at the centre.
← Most of the time spent working on software goes to reading,…
17 connected korrents · 16 moments on record from 4 Feb 2020 to 6 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under AI writing
AI writing
Everything filed under Anthropic
Anthropic
Everything filed under code generation
code generation
Everything filed under vibe coding
vibe coding
Everything filed under software quality
software quality 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: Most of the time spent working on software goes to reading, understanding and editing existing code, not writing new code. Most of the time spent working on software goes to reading, understanding and editing existing code, not writing new code. Last stated 7 years ago
4 Feb 2020
TB
Thorsten Ball — holds since 2020-02-04 — tap for who they are
Same subject: You cannot really understand the code you write unless you are also the one operating it. — tap to centre the map on it You cannot really understand the code you write unless you are also the one operating it. Last stated a month ago
12 Aug 2026
CM
Charity Majors — holds since 2026-08-12 — tap for who they are
Same subject: A sense of achievement in software survives writing almost none of the code yourself. — tap to centre the map on it A sense of achievement in software survives writing almost none of the code yourself. Last stated 4 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: Software only gets good by being used a lot by the people building it, so time spent inside coding agents instead of the app is time that makes the app worse. — tap to centre the map on it Software only gets good by being used a lot by the people building it, so time spent inside coding agents instead of the app is time that makes the app worse. Last stated 2 weeks ago
6 Sept 2026
BV
Ben Vinegar — holds since 2026-09-06 — tap for who they are
Same subject: He does not read the boring parts of generated code, the data-shuffling and button alignment; what touches the database he reads and reviews. — tap to centre the map on it He does not read the boring parts of generated code, the data-shuffling and button alignment; what touches the database he reads and reviews. Last stated 7 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Most of software is not the new stuff; it is old, crappy code somebody has to maintain, and it is full of genuinely hard problems. — tap to centre the map on it Most of software is not the new stuff; it is old, crappy code somebody has to maintain, and it is full of genuinely hard problems. Last stated a year ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — 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 3 months ago
1 Jul 2026
KB
Kent Beck — holds since 2026-07-01 — tap for who they are
Same subject: Writing software far better than most of what ships today does not take an expert: you do not have to know very much at all. — tap to centre the map on it Writing software far better than most of what ships today does not take an expert: you do not have to know very much at all. Last stated 4 weeks ago
26 Aug 2026
CM
Casey Muratori — holds since 2026-08-26 — tap for who they are
Same subject: It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times. — tap to centre the map on it It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times. Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — 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 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 2 weeks ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A company on a monolith cannot use AI on it: no model in the next eighteen months will hold that codebase, so the monolith has to be broken up or rewritten. — tap to centre the map on it A company on a monolith cannot use AI on it: no model in the next eighteen months will hold that codebase, so the monolith has to be broken up or rewritten. Last stated 6 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent. — tap to centre the map on it A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent. Last stated 3 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: AI content should be labelled rather than filtered: content should be judged by its point of view, never by the tool that made it. — tap to centre the map on it AI content should be labelled rather than filtered: content should be judged by its point of view, never by the tool that made it. Last stated 2 months ago
9 Jul 2026
AM
Adam Mosseri — holds since 2026-07-09 — tap for who they are
Same subject: AI has done the first ninety per cent of the work of sounding human, and the last five per cent will turn out to be about ninety-five per cent of the work. — tap to centre the map on it AI has done the first ninety per cent of the work of sounding human, and the last five per cent will turn out to be about ninety-five per cent of the work. Last stated 11 months ago
31 Oct 2025
DH
Dan Houser — holds since 2025-10-31 — 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 weeks 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 produces. Last stated 3 weeks 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 dual-class shares. Last stated 4 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — tap for who they are
At the centre
Most of the time spent working on software goes to reading, understanding and editing existing code, not writing new code.
Holds Read this korrent →
You cannot really understand the code you write unless you are also the one operating it.
Holds
A sense of achievement in software survives writing almost none of the code yourself.
Holds
Software only gets good by being used a lot by the people building it, so time spent inside coding agents instead of the app is time that makes the app worse.
Holds
He does not read the boring parts of generated code, the data-shuffling and button alignment; what touches the database he reads and reviews.
Holds
Most of software is not the new stuff; it is old, crappy code somebody has to maintain, and it is full of genuinely hard problems.
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
Writing software far better than most of what ships today does not take an expert: you do not have to know very much at all.
Holds
It is no longer worth not reading the code in exchange for the occasional two-week hand fix, because the volume of code we can now generate has gone up ten to a hundred times.
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 company should not train its own model: it has to stay neutral ground for models to compete on.
Holds
A company on a monolith cannot use AI on it: no model in the next eighteen months will hold that codebase, so the monolith has to be broken up or rewritten.
Holds
A stream of AI-written papers with any error rate at all becomes insufferable, because finding the error costs more than the paper is worth even at ninety-nine percent.
Holds
AI content should be labelled rather than filtered: content should be judged by its point of view, never by the tool that made it.
Holds
AI has done the first ninety per cent of the work of sounding human, and the last five per cent will turn out to be about ninety-five per cent of the work.
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