Tap a claim on the ring to put it at the centre.
← Traditional programming rewarded sustained attention to one problem,…
17 connected korrents · 16 moments from 18 Aug 2025 to 27 Sept 2026. Nearly all of them are about coding agents .
Everything filed under LLMs
LLMs
Everything filed under empathy
empathy
Everything filed under vibe coding
vibe coding
Everything filed under AI agents
AI 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: Traditional programming rewarded sustained attention to one problem, while agentic programming rewards how much work can be kept moving before usage limits reset. Traditional programming rewarded sustained attention to one problem, while agentic programming rewards how much work can be kept moving before usage limits reset. Last stated 2 months ago
19 Aug 2026
KR
Kenneth Reitz — holds since 2026-08-19 — tap for who they are
Same subject: You cannot know what a program should do until you play with it, so in the agentic age you should be as vague as you can up front and then interact with what appears. — tap to centre the map on it You cannot know what a program should do until you play with it, so in the agentic age you should be as vague as you can up front and then interact with what appears. Last stated 2 months ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: There is no accumulated advantage in agentic coding: someone who ignored the whole of the past year could catch up to the frontier in two weeks. — tap to centre the map on it There is no accumulated advantage in agentic coding: someone who ignored the whole of the past year could catch up to the frontier in two weeks. Last stated 2 months ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: Every abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them. — tap to centre the map on it Every abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Maintaining a duplicate set of prototype code is no burden for an agent; agents are incredibly good translators between code conventions. — tap to centre the map on it Maintaining a duplicate set of prototype code is no burden for an agent; agents are incredibly good translators between code conventions. Last stated 2 months ago
18 Aug 2026
PM
Patrick Morgan — holds since 2026-08-18 — tap for who they are
Same subject: Asked to find a deep bug, coding agents can patch many small issues that feel like progress while steering you away from the real problem; there is still no substitute for expertise. — tap to centre the map on it Asked to find a deep bug, coding agents can patch many small issues that feel like progress while steering you away from the real problem; there is still no substitute for expertise. Last stated 3 months ago
5 Aug 2026
BV
Ben Vinegar — holds since 2026-08-05 — 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 8 months ago
12 Feb 2026
LF
Lex Fridman — holds since 2026-02-12 — tap for who they are
Same subject: If you want loop engineering, build one loop at a time and keep them small: every part of the agentic-factory playbook is good advice except the part where you stop reading the code. — tap to centre the map on it If you want loop engineering, build one loop at a time and keep them small: every part of the agentic-factory playbook is good advice except the part where you stop reading the code. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The value of agentic coding tools comes from how you configure and constrain them, not from raw code generation. — tap to centre the map on it The value of agentic coding tools comes from how you configure and constrain them, not from raw code generation. Last stated 9 months ago
6 Feb 2026
AK
Arvid Kahl — holds since 2026-02-06 — tap for who they are
Same subject: Agents are good at producing output but not at judging which output is worth producing in the first place. — tap to centre the map on it Agents are good at producing output but not at judging which output is worth producing in the first place. Last stated 4 weeks ago
24 Sept 2026
KD
Kent C. Dodds — holds since 2026-09-24 — tap for who they are
Same subject: Agents will take a decade rather than a year, because today's models are cognitively lacking in too many independent ways at once. — tap to centre the map on it Agents will take a decade rather than a year, because today's models are cognitively lacking in too many independent ways at once. Last stated a year ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: AI needs the same coaching, context and onboarding as a human employee. — tap to centre the map on it AI needs the same coaching, context and onboarding as a human employee. Last stated 4 weeks ago
27 Sept 2026
MG
Molly Graham — holds since 2026-09-27 — tap for who they are
Same subject: AI systems built on statistical inference cannot form intent, because they have nothing with which to form it. — tap to centre the map on it AI systems built on statistical inference cannot form intent, because they have nothing with which to form it. Last stated a month ago
21 Sept 2026
CD
Cory Doctorow — holds since 2026-09-21 — tap for who they are
Same subject: AI systems can now directly interact with the tools on a person's computer and browser, not just generate text. — tap to centre the map on it AI systems can now directly interact with the tools on a person's computer and browser, not just generate text. Last stated 2 months ago
13 Aug 2026
TF
Tiago Forte — holds since 2026-08-13 — tap for who they are
Same subject: An application-layer AI company's real breakthroughs come from going a click or two down the stack rather than from using the models as they are. — tap to centre the map on it An application-layer AI company's real breakthroughs come from going a click or two down the stack rather than from using the models as they are. Last stated a year ago
18 Aug 2025
CB
Clay Bavor — holds since 2025-08-18 — tap for who they are
Same subject: Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. — tap to centre the map on it Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. Last stated 9 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: The best way to build an AI agent skill is to do the work manually first, then have the AI turn that work into a reusable skill. — tap to centre the map on it The best way to build an AI agent skill is to do the work manually first, then have the AI turn that work into a reusable skill. Last stated 7 months ago
11 Mar 2026
HR
Harper Reed — holds since 2026-03-11 — tap for who they are
Same subject: A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first. — tap to centre the map on it A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first. Last stated 4 months ago
16 Jun 2026
BW
Brett Williams — holds since 2026-06-16 — tap for who they are
At the centre
Traditional programming rewarded sustained attention to one problem, while agentic programming rewards how much work can be kept moving before usage limits reset.
Holds Read this korrent →
You cannot know what a program should do until you play with it, so in the agentic age you should be as vague as you can up front and then interact with what appears.
Holds
There is no accumulated advantage in agentic coding: someone who ignored the whole of the past year could catch up to the frontier in two weeks.
Holds
Every abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them.
Holds
Maintaining a duplicate set of prototype code is no burden for an agent; agents are incredibly good translators between code conventions.
Holds
Asked to find a deep bug, coding agents can patch many small issues that feel like progress while steering you away from the real problem; there is still no substitute for expertise.
Holds
Being an excellent programmer is a burden rather than an advantage when learning to work with coding agents.
Holds
If you want loop engineering, build one loop at a time and keep them small: every part of the agentic-factory playbook is good advice except the part where you stop reading the code.
Holds
The value of agentic coding tools comes from how you configure and constrain them, not from raw code generation.
Holds
Agents are good at producing output but not at judging which output is worth producing in the first place.
Holds
Agents will take a decade rather than a year, because today's models are cognitively lacking in too many independent ways at once.
Holds
AI needs the same coaching, context and onboarding as a human employee.
Holds
AI systems built on statistical inference cannot form intent, because they have nothing with which to form it.
Holds
AI systems can now directly interact with the tools on a person's computer and browser, not just generate text.
Holds
An application-layer AI company's real breakthroughs come from going a click or two down the stack rather than from using the models as they are.
Holds
Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.
Holds
The best way to build an AI agent skill is to do the work manually first, then have the AI turn that work into a reusable skill.
Holds
A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first.
Holds