Tap a claim on the ring to put it at the centre.
← The best way to build an AI agent skill is to do the work manually…
17 connected korrents · 16 moments from 18 Aug 2025 to 24 Sept 2026. Nearly all of them are about Anthropic .
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under benchmarks
benchmarks
Everything filed under chat interfaces
chat interfaces
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: 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. 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 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 4 weeks 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 4 weeks ago
2 Sept 2026
SW
Simon Willison — holds since 2026-09-02 — tap for who they are
Same subject: A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. — tap to centre the map on it A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. Last stated a month ago
30 Aug 2026
EP
Eliot Peper — holds since 2026-08-30 — tap for who they are
Same subject: A tool for browsing personal notes and data works better with a conversational interface than a traditional file browser. — tap to centre the map on it A tool for browsing personal notes and data works better with a conversational interface than a traditional file browser. Last stated 7 months ago
11 Mar 2026
HR
Harper Reed — holds since 2026-03-11 — 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 5 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — tap for who they are
Same subject: Adding all files to git and then diffing them is a heavy-handed option for models editing files. — tap to centre the map on it Adding all files to git and then diffing them is a heavy-handed option for models editing files. Last stated a week ago
24 Sept 2026
AR
Armin Ronacher — holds since 2026-09-24 — tap for who they are
Same subject: Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million. — tap to centre the map on it Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million. Last stated 7 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: AI agents and AI coding will run on servers and from the cloud first, not on your laptop. — tap to centre the map on it AI agents and AI coding will run on servers and from the cloud first, not on your laptop. Last stated 3 months ago
28 Jun 2026
PL
Pieter Levels — holds since 2026-06-28 — 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 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — 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: Any AI-driven action is legally defensible if it followed a revocable moment of user consent. — tap to centre the map on it Any AI-driven action is legally defensible if it followed a revocable moment of user consent. Last stated 6 months ago
20 Mar 2026
AK
Arvid Kahl — holds since 2026-03-20 — tap for who they are
Same subject: As AI inference costs fall, rising customer expectations will keep service margins from converging toward 100%. — tap to centre the map on it As AI inference costs fall, rising customer expectations will keep service margins from converging toward 100%. Last stated 2 weeks ago
17 Sept 2026
TT
Tomasz Tunguz — holds since 2026-09-17 — tap for who they are
Same subject: As AI labs aim for broad, general capability, handling messy real-world bureaucratic tasks is becoming a primary application domain for their models. — tap to centre the map on it As AI labs aim for broad, general capability, handling messy real-world bureaucratic tasks is becoming a primary application domain for their models. Last stated 4 months ago
25 May 2026
RK
Rohit Krishnan — holds since 2026-05-25 — 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 agents were reasonable to assume a broken exploit grader would check results causally, even though it turned out not to. — tap to centre the map on it AI agents were reasonable to assume a broken exploit grader would check results causally, even though it turned out not to. Last stated a month ago
29 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-29 — tap for who they are
Same subject: AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation. — tap to centre the map on it AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation. Last stated 3 weeks ago
10 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-10 — tap for who they are
At the centre
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 Read this korrent →
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 story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it.
Holds
A tool for browsing personal notes and data works better with a conversational interface than a traditional file browser.
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
Adding all files to git and then diffing them is a heavy-handed option for models editing files.
Holds
Agents can build about half a million lines before the codebase dissolves into a mess, and the next model will push that to a few million.
Holds
AI agents and AI coding will run on servers and from the cloud first, not on your laptop.
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 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
Any AI-driven action is legally defensible if it followed a revocable moment of user consent.
Holds
As AI inference costs fall, rising customer expectations will keep service margins from converging toward 100%.
Holds
As AI labs aim for broad, general capability, handling messy real-world bureaucratic tasks is becoming a primary application domain for their models.
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 agents were reasonable to assume a broken exploit grader would check results causally, even though it turned out not to.
Holds
AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation.
Holds