Tap a claim on the ring to put it at the centre.
← The failure mode of experienced engineers with AI is over-specifying:…
17 connected korrents · 17 moments on record from 11 Jun 2006 to 3 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under simplicity
simplicity
Everything filed under taste
taste
Everything filed under design
design
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: The failure mode of experienced engineers with AI is over-specifying: telling the model to do the task exactly the way they would have done it.
The failure mode of experienced engineers with AI is over-specifying: telling the model to do the task exactly the way they would have done it.
Last stated a month ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. — tap to centre the map on it
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — tap for who they are
Same subject: Over-specifying a design makes it harder to estimate, not easier: the more specific the work, the more hidden complexity a mockup commits the team to. — tap to centre the map on it
Over-specifying a design makes it harder to estimate, not easier: the more specific the work, the more hidden complexity a mockup commits the team to.
Last stated 7 years ago
by 10 Jul 2019
RS
Ryan Singer — holds since 2019-07-10 — tap for who they are
Same subject: Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. — tap to centre the map on it
Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before.
Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — 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: AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's. — tap to centre the map on it
AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's.
Last stated a month ago
29 Jul 2026
HW
Hillel Wayne — holds since 2026-07-29 — tap for who they are
Same subject: AI models have reached the level of a junior engineer on longer-running, agent-based coding tasks. — tap to centre the map on it
AI models have reached the level of a junior engineer on longer-running, agent-based coding tasks.
Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — 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 year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite. — tap to centre the map on it
A year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite.
Last stated 3 months ago
24 May 2026
DS
Dan Shipper — holds since 2026-05-24 — 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 4 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 3 weeks ago
14 Aug 2026
SP
Sunil Pai — holds since 2026-08-14 — 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: Convergence and simplicity make for poor goals in technology; aim for clarity instead. — tap to centre the map on it
Convergence and simplicity make for poor goals in technology; aim for clarity instead.
Last stated 12 years ago
18 Feb 2015
FC
Frank Chimero — holds since 2015-02-18 — tap for who they are
Same subject: Savings in time feel like simplicity: when forced to wait, life seems unnecessarily complex. — tap to centre the map on it
Savings in time feel like simplicity: when forced to wait, life seems unnecessarily complex.
Last stated 20 years ago
11 Jun 2006
JM
John Maeda — holds since 2006-06-11 — tap for who they are
Same subject: A first draft should not be graded good or bad; it is only the material that taste then gets to act on. — tap to centre the map on it
A first draft should not be graded good or bad; it is only the material that taste then gets to act on.
Last stated a month ago
6 Aug 2026
GS
George Saunders — holds since 2026-08-06 — tap for who they are
Same subject: A lot of people can match a framework for taste; almost nobody can create one, and creating one is the rare skill. — tap to centre the map on it
A lot of people can match a framework for taste; almost nobody can create one, and creating one is the rare skill.
Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — tap for who they are
Same subject: A product needs a soul, and for that it needs one person of great taste who is its living, breathing aspect and gets furious about every small detail. — tap to centre the map on it
A product needs a soul, and for that it needs one person of great taste who is its living, breathing aspect and gets furious about every small detail.
Last stated 17 years ago
12 Feb 2010
KS
Karri Saarinen — holds since 2010-02-12 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2006 to today (stretched back to the oldest claim here) — full is today a face: someone on record holding the claim — tap it for who they are
At the centre
The failure mode of experienced engineers with AI is over-specifying: telling the model to do the task exactly the way they would have done it.
Last stated 27 Jul 2026 · a month ago
Holds Boris Cherny
Read this korrent →
Similar wording
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
Last stated 16 Oct 2025 · 11 months ago
Holds DF Dylan Field
Similar wording
Over-specifying a design makes it harder to estimate, not easier: the more specific the work, the more hidden complexity a mockup commits the team to.
Last stated by 10 Jul 2019 · 7 years ago
Holds RS Ryan Singer
Similar wording
Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before.
Last stated 17 Oct 2025 · 11 months ago
Holds Andrej Karpathy
Similar wording
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 19 Jul 2026 · 2 months ago
Holds ES Elizabeth Stone
Similar wording
AI does a good job of generating a design and still cannot express what the design is supposed to do; that part is the engineer's.
Last stated 29 Jul 2026 · a month ago
Holds HW Hillel Wayne
Similar wording
AI models have reached the level of a junior engineer on longer-running, agent-based coding tasks.
Last stated 30 Jul 2026 · a month ago
Holds JD Jeff Dean
Similar wording
What limits you with coding agents is your own skill at stringing them together, not the capability of the models.
Last stated 20 Mar 2026 · 6 months ago
Holds Andrej Karpathy
Similar wording
A year from now every coding model on the market will still take a bad instruction at face value and go fix the listed issues, where a human senior engineer would insist on a rewrite.
Last stated 24 May 2026 · 3 months ago
Holds DS Dan Shipper
Same subject: coding agents
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 25 Mar 2026 · 5 months ago
Holds Mario Zechner
Same subject: coding agents
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.
Last stated 3 Sept 2026 · 4 days ago
Holds Dax Raad
Same subject: coding agents
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 14 Aug 2026 · 3 weeks ago
Holds Sunil Pai
Same subject: simplicity
AI acceleration threatens 'less software': without the constraint of scarce hours, even 37signals will likely build too much.
Last stated 26 Jul 2026 · a month ago
Holds David Heinemeier Hansson
Same subject: simplicity
Convergence and simplicity make for poor goals in technology; aim for clarity instead.
Last stated 18 Feb 2015 · 12 years ago
Holds FC Frank Chimero
Same subject: simplicity
Savings in time feel like simplicity: when forced to wait, life seems unnecessarily complex.
Last stated 11 Jun 2006 · 20 years ago
Holds JM John Maeda
Same subject: taste
A first draft should not be graded good or bad; it is only the material that taste then gets to act on.
Last stated 6 Aug 2026 · a month ago
Holds GS George Saunders
Same subject: taste
A lot of people can match a framework for taste; almost nobody can create one, and creating one is the rare skill.
Last stated 16 Oct 2025 · 11 months ago
Holds DF Dylan Field
Same subject: taste
A product needs a soul, and for that it needs one person of great taste who is its living, breathing aspect and gets furious about every small detail.
Last stated 12 Feb 2010 · 17 years ago
Holds KS Karri Saarinen