Tap a claim on the ring to put it at the centre.
← Agents are good at producing output but not at judging which output is worth producing in the first place.
17 connected korrents · 19 moments from 16 Jan 2023 to 31 Oct 2026.
Everything filed under AI agents
AI agents
Everything filed under LLMs
LLMs
Everything filed under coding agents
coding agents
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: Agents are good at producing output but not at judging which output is worth producing in the first place.
Agents are good at producing output but not at judging which output is worth producing in the first place.
Last stated 2 months ago
24 Sept 2026
KD
Kent C. Dodds — holds since 2026-09-24 — tap for who they are
Same subject: Coding agents are good enough to take on a huge task without being told so. — tap to centre the map on it
Coding agents are good enough to take on a huge task without being told so.
Last stated 2 months ago
6 Oct 2026
KD
Kent C. Dodds — holds since 2026-10-06 — tap for who they are
Same subject: AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them. — tap to centre the map on it
AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them.
Last stated 2 months ago
14 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-14 — tap for who they are
Same subject: An agent can tell you whether a thing looks correct against a spec; it cannot tell you whether the thing is any good. — tap to centre the map on it
An agent can tell you whether a thing looks correct against a spec; it cannot tell you whether the thing is any good.
Last stated 3 months ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: AI agents cannot be perfectly isolated if they are to be useful, because their usefulness depends on access to information. — tap to centre the map on it
AI agents cannot be perfectly isolated if they are to be useful, because their usefulness depends on access to information.
Last stated 2 months ago
30 Sept 2026
MG
Matthew Green — holds since 2026-09-30 — tap for who they are
Same subject: The more capable an agent is made, the more it can do on its own without the person shuttling context to it. — tap to centre the map on it
The more capable an agent is made, the more it can do on its own without the person shuttling context to it.
Last stated 2 months ago
15 Sept 2026
KD
Kent C. Dodds — holds since 2026-09-15 — tap for who they are
Same subject: Agents are now good enough to verify their own changes the way engineers have, by going to the browser and clicking around. — tap to centre the map on it
Agents are now good enough to verify their own changes the way engineers have, by going to the browser and clicking around.
Last stated a month ago
13 Oct 2026
KD
Kent C. Dodds — holds since 2026-10-13 — tap for who they are
Same subject: Agents can set up measurement and feedback work but do not propose it; you have to know to ask. — tap to centre the map on it
Agents can set up measurement and feedback work but do not propose it; you have to know to ask.
Last stated 3 months ago
25 Aug 2026
NE
NeetCode — holds since 2026-08-25 — tap for who they are
Same subject: Inconsistent output from an AI product is not necessarily bad; it is how AI behaves. — tap to centre the map on it
Inconsistent output from an AI product is not necessarily bad; it is how AI behaves.
Last stated 3 weeks ago
31 Oct 2026
MN
Marily Nika — holds since 2026-10-31 — tap for who they are
Same subject: A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop. — tap to centre the map on it
A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop.
Last stated 5 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — tap for who they are
Same subject: AI has no genuine discernment; it absorbs and reproduces without judgment. — tap to centre the map on it
AI has no genuine discernment; it absorbs and reproduces without judgment.
Last stated 3 months ago
10 Aug 2026
AH
Ann Handley — holds since 2026-08-10 — tap for who they are
Same subject: AI is like the most patient collaborator you could have, building at hyper speeds, if you know how to direct it and bring taste and judgment on what to build and how, down to the finest UX and UI decisions. — tap to centre the map on it
AI is like the most patient collaborator you could have, building at hyper speeds, if you know how to direct it and bring taste and judgment on what to build and how, down to the finest UX and UI decisions.
Last stated 5 months ago
16 Jun 2026
BW
Brett Williams — holds since 2026-06-16 — tap for who they are
Same subject: AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right. — tap to centre the map on it
AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right.
Last stated 6 months ago
26 May 2026
CB
Carlos Alexandro Becker — holds since 2026-05-26 — tap for who they are
Same subject: AI models default to generic, lowest-common-denominator output unless a user actively pushes back against them. — tap to centre the map on it
AI models default to generic, lowest-common-denominator output unless a user actively pushes back against them.
Last stated 5 months ago
29 Jun 2026
KC
Kyle Chayka — holds since 2026-06-29 — tap for who they are
Same subject: LLMs push the cost of translation work close to zero, while humans still provide judgment, taste and accountability. — tap to centre the map on it
LLMs push the cost of translation work close to zero, while humans still provide judgment, taste and accountability.
Last stated a year ago
12 Sept 2025
AC
Aparna Chennapragada — holds since 2025-09-12 — tap for who they are
Same subject: What a generative model makes is a replication of art rather than art, because it can only imitate or average the choices human makers have already made. — tap to centre the map on it
What a generative model makes is a replication of art rather than art, because it can only imitate or average the choices human makers have already made.
Last stated 2 years ago
31 Aug 2024
TC
Ted Chiang — holds since 2024-08-31 — tap for who they are
NC
Nick Cave — holds since 2023-01-16 — tap for who they are
Same subject: A model claiming to be built by OpenAI is not necessarily evidence that it was trained on OpenAI data. — tap to centre the map on it
A model claiming to be built by OpenAI is not necessarily evidence that it was trained on OpenAI data.
Last stated 2 years ago
5 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-05 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Last stated 9 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — 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 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
Agents are good at producing output but not at judging which output is worth producing in the first place.
Last stated 24 Sept 2026 · 2 months ago
Holds Kent C. Dodds
Read this korrent →
Similar wording
Coding agents are good enough to take on a huge task without being told so.
Last stated 6 Oct 2026 · 2 months ago
Holds Kent C. Dodds
Similar wording
AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them.
Last stated 14 Sept 2026 · 2 months ago
Holds Guillermo Rauch
Similar wording
An agent can tell you whether a thing looks correct against a spec; it cannot tell you whether the thing is any good.
Last stated 19 Aug 2026 · 3 months ago
Holds Addy Osmani
Similar wording
AI agents cannot be perfectly isolated if they are to be useful, because their usefulness depends on access to information.
Last stated 30 Sept 2026 · 2 months ago
Holds Matthew Green
Similar wording
The more capable an agent is made, the more it can do on its own without the person shuttling context to it.
Last stated 15 Sept 2026 · 2 months ago
Holds Kent C. Dodds
Similar wording
Agents are now good enough to verify their own changes the way engineers have, by going to the browser and clicking around.
Last stated 13 Oct 2026 · a month ago
Holds Kent C. Dodds
Similar wording
Agents can set up measurement and feedback work but do not propose it; you have to know to ask.
Last stated 25 Aug 2026 · 3 months ago
Holds NeetCode
Similar wording
Inconsistent output from an AI product is not necessarily bad; it is how AI behaves.
Last stated 31 Oct 2026 · 3 weeks ago
Holds Marily Nika
Same subject: LLMs
A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop.
Last stated 30 Jun 2026 · 5 months ago
Holds Meng To
Same subject: LLMs
AI has no genuine discernment; it absorbs and reproduces without judgment.
Last stated 10 Aug 2026 · 3 months ago
Holds Ann Handley
Same subject: LLMs
AI is like the most patient collaborator you could have, building at hyper speeds, if you know how to direct it and bring taste and judgment on what to build and how, down to the finest UX and UI decisions.
Last stated 16 Jun 2026 · 5 months ago
Holds Brett Williams
Same subject: taste
AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right.
Last stated 26 May 2026 · 6 months ago
Holds Carlos Alexandro Becker
Same subject: taste
AI models default to generic, lowest-common-denominator output unless a user actively pushes back against them.
Last stated 29 Jun 2026 · 5 months ago
Holds Kyle Chayka
Same subject: taste
LLMs push the cost of translation work close to zero, while humans still provide judgment, taste and accountability.
Last stated 12 Sept 2025 · a year ago
Holds Aparna Chennapragada
Same subject: OpenAI
What a generative model makes is a replication of art rather than art, because it can only imitate or average the choices human makers have already made.
Last stated 31 Aug 2024 · 2 years ago
Holds Ted Chiang Nick Cave
Same subject: OpenAI
A model claiming to be built by OpenAI is not necessarily evidence that it was trained on OpenAI data.
Last stated 5 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Same subject: OpenAI
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Last stated 12 Feb 2026 · 9 months ago
Holds Andrej Karpathy