Tap a claim on the ring to put it at the centre.
← Specifying an edit by line number alone is fragile because a model can misremember what that line contains.
17 connected korrents · 15 moments from 21 Mar 2023 to 17 Oct 2026.
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs
Everything filed under compilers
compilers
Everything filed under writing
writing
Everything filed under MCP
MCP
Everything filed under AGI
AGI
Everything filed under Python
Python 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: Specifying an edit by line number alone is fragile because a model can misremember what that line contains. Specifying an edit by line number alone is fragile because a model can misremember what that line contains. Last stated 5 months ago
19 May 2026
SS
Salvatore Sanfilippo — holds since 2026-05-19 — 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 3 months ago
19 Jul 2026
ES
Elizabeth Stone — holds since 2026-07-19 — tap for who they are
Same subject: A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting. — tap to centre the map on it A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting. Last stated 5 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — tap for who they are
Same subject: A plan that spells out every line of code to change gives you no leverage: it costs as long to read as the pull request, so you end up skimming it and reading the code twice. — tap to centre the map on it A plan that spells out every line of code to change gives you no leverage: it costs as long to read as the pull request, so you end up skimming it and reading the code twice. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Editing your writing with a model pulls it towards one homogeneous style, far enough that you lose track of what your own voice was. — tap to centre the map on it Editing your writing with a model pulls it towards one homogeneous style, far enough that you lose track of what your own voice was. Last stated 2 months ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context. — tap to centre the map on it Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context. Last stated 8 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: It is now much faster and easier to change code than it was years ago. — tap to centre the map on it It is now much faster and easier to change code than it was years ago. Last stated a week ago
17 Oct 2026
TB
Thorsten Ball — holds since 2026-10-17 — tap for who they are
Same subject: Quoting a number for P(doom) is a ridiculous notion, because it implies a precision that nobody actually has. — tap to centre the map on it Quoting a number for P(doom) is a ridiculous notion, because it implies a precision that nobody actually has. Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: A language can keep changing without a Python-2-to-3 break, as long as code written under the old and the new rules can be mixed freely in one program. — tap to centre the map on it A language can keep changing without a Python-2-to-3 break, as long as code written under the old and the new rules can be mixed freely in one program. Last stated 5 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 10 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated a month ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — 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
Same subject: Among the misuse threats in Anthropic's threat disruption report, distillation is by far the most important and will have the most impact. — tap to centre the map on it Among the misuse threats in Anthropic's threat disruption report, distillation is by far the most important and will have the most impact. Last stated a month ago
15 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-15 — tap for who they are
Same subject: Anthropic prices its Claude subscription plans as loss leaders relative to its own API rates. — tap to centre the map on it Anthropic prices its Claude subscription plans as loss leaders relative to its own API rates. Last stated a month ago
19 Sept 2026
BD
Brad DeLong — holds since 2026-09-19 — 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 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. — tap to centre the map on it An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. Last stated 4 years ago
21 Mar 2023
BC
Bryan Caplan — holds since 2023-03-21 — tap for who they are
At the centre
Specifying an edit by line number alone is fragile because a model can misremember what that line contains.
Holds Read this korrent →
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
A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting.
Holds
A plan that spells out every line of code to change gives you no leverage: it costs as long to read as the pull request, so you end up skimming it and reading the code twice.
Holds
Editing your writing with a model pulls it towards one homogeneous style, far enough that you lose track of what your own voice was.
Holds
Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context.
Holds
It is now much faster and easier to change code than it was years ago.
Holds
Quoting a number for P(doom) is a ridiculous notion, because it implies a precision that nobody actually has.
Holds
A language can keep changing without a Python-2-to-3 break, as long as code written under the old and the new rules can be mixed freely in one program.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds
A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first.
Holds
Among the misuse threats in Anthropic's threat disruption report, distillation is by far the most important and will have the most impact.
Holds
Anthropic prices its Claude subscription plans as loss leaders relative to its own API rates.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
Holds