Tap a claim on the ring to put it at the centre.
← Having an AI agent write tests costs tokens in the short run and saves…
17 connected korrents · 14 moments on record from 15 Oct 2019 to 3 Sept 2026.
Everything filed under code generation
code generation
Everything filed under coding agents
coding agents
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: Having an AI agent write tests costs tokens in the short run and saves them in the long run, because the classic failure is that the code does not work. Having an AI agent write tests costs tokens in the short run and saves them in the long run, because the classic failure is that the code does not work. Last stated 2 months ago
1 Jul 2026
KB
Kent Beck — holds since 2026-07-01 — tap for who they are
Same subject: When an AI agent runs out of forward progress, throw the project away and start over rather than trying to tweak it. — tap to centre the map on it When an AI agent runs out of forward progress, throw the project away and start over rather than trying to tweak it. Last stated 2 months ago
1 Jul 2026
KB
Kent Beck — holds since 2026-07-01 — tap for who they are
Same subject: The case for sweating every line of code was premised on humans doing the modifications, and it now survives only because tokens are scarce. — tap to centre the map on it The case for sweating every line of code was premised on humans doing the modifications, and it now survives only because tokens are scarce. Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. — tap to centre the map on it In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. Last stated 5 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. — tap to centre the map on it The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. Last stated 2 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — tap for who they are
Same subject: Token prices have stayed flat because labs deliberately kept models smaller than expected in order to get more experimental cycles. — tap to centre the map on it Token prices have stayed flat because labs deliberately kept models smaller than expected in order to get more experimental cycles. Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — 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: Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop. — tap to centre the map on it Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop. Last stated 3 months ago
7 Jun 2026
TF
Tony Fadell — holds since 2026-06-07 — tap for who they are
Same subject: AI coding works when a person owns the architecture and scopes the agent to small pieces of it, and fails when the whole thing is handed over. — tap to centre the map on it AI coding works when a person owns the architecture and scopes the agent to small pieces of it, and fails when the whole thing is handed over. Last stated 3 months ago
7 Jun 2026
TF
Tony Fadell — holds since 2026-06-07 — tap for who they are
Same subject: AI acceleration threatens 'less software': without the constraint of scarce hours, even 37signals will likely build too much. — tap to centre the map on it AI acceleration threatens 'less software': without the constraint of scarce hours, even 37signals will likely build too much. Last stated a month ago
26 Jul 2026
DH
David Heinemeier Hansson — holds since 2026-07-26 — tap for who they are
Same subject: AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. — tap to centre the map on it AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. Last stated 5 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — tap for who they are
Same subject: Code and files generated by tools are pollution: hand-writing them is worth the effort because the bloat slows everything down for everyone. — tap to centre the map on it Code and files generated by tools are pollution: hand-writing them is worth the effort because the bloat slows everything down for everyone. Last stated 7 years ago
15 Oct 2019
DS
Derek Sivers — holds since 2019-10-15 — 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 5 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 5 days ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its tasks are so legible and verifiable. — tap to centre the map on it A machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its tasks are so legible and verifiable. Last stated 4 weeks ago
14 Aug 2026
SP
Sunil Pai — holds since 2026-08-14 — 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 5 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 produces. Last stated 6 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 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
Having an AI agent write tests costs tokens in the short run and saves them in the long run, because the classic failure is that the code does not work.
Holds KB Kent BeckRead this korrent →
When an AI agent runs out of forward progress, throw the project away and start over rather than trying to tweak it.
Holds KB Kent Beck
The case for sweating every line of code was premised on humans doing the modifications, and it now survives only because tokens are scarce.
Holds
In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works.
Holds
The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks.
Holds ES Elizabeth Stone
Token prices have stayed flat because labs deliberately kept models smaller than expected in order to get more experimental cycles.
Holds RG Ryan Greenblatt
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 BT Bret Taylor
Agent-written code that runs and passes its tests is not enough: security, maintainability and being able to roll it back still need humans in the loop.
Holds TF Tony Fadell
AI coding works when a person owns the architecture and scopes the agent to small pieces of it, and fails when the whole thing is handed over.
Holds TF Tony Fadell
AI acceleration threatens 'less software': without the constraint of scarce hours, even 37signals will likely build too much.
Holds
AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck.
Holds MK Martin Kleppmann
Code and files generated by tools are pollution: hand-writing them is worth the effort because the bloat slows everything down for everyone.
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 machine can complete the task and completely miss the job -- coding makes this easy to see precisely because its tasks are so legible and verifiable.
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