Tap a claim on the ring to put it at the centre.
← Making a capable model malicious is about as easy as making it…
17 connected korrents · 16 moments from 10 Jun 2025 to 18 Oct 2026. Nearly all of them are about Anthropic .
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under AI alignment
AI alignment
Everything filed under coding agents
coding agents
Everything filed under benchmarks
benchmarks
Everything filed under chat interfaces
chat interfaces 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: Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. 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: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. Last stated 8 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — 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 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 8 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — 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 2 months ago
30 Aug 2026
EP
Eliot Peper — holds since 2026-08-30 — 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 5 months ago
16 Jun 2026
BW
Brett Williams — holds since 2026-06-16 — 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 8 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 6 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — 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 8 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — 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: Reasoning models trained on verifiable rewards automatically gain greater autonomy and long-horizon planning ability as a side effect. — tap to centre the map on it Reasoning models trained on verifiable rewards automatically gain greater autonomy and long-horizon planning ability as a side effect. Last stated a year ago
10 Jun 2025
SH
Samuel Hammond — holds since 2025-06-10 — tap for who they are
Same subject: A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish. — tap to centre the map on it A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish. Last stated 2 months ago
20 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-20 — tap for who they are
Same subject: A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation. — tap to centre the map on it A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation. Last stated a month ago
22 Sept 2026
HR
Harper Reed — holds since 2026-09-22 — tap for who they are
Same subject: Agents become far more powerful only with a trust model that makes autonomous action safe. — tap to centre the map on it Agents become far more powerful only with a trust model that makes autonomous action safe. Last stated 3 weeks ago
18 Oct 2026
AK
Alex Komoroske — holds since 2026-10-18 — tap for who they are
Same subject: AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. — tap to centre the map on it AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. Last stated 3 months ago
10 Aug 2026
JC
Jack Clark — holds since 2026-08-10 — 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 a month 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 misbehavior, where a narrow well-defined goal wins out over vaguer values like not cheating, may be an inherent feature of current LLM technology rather than a fixable bug. — tap to centre the map on it AI misbehavior, where a narrow well-defined goal wins out over vaguer values like not cheating, may be an inherent feature of current LLM technology rather than a fixable bug. Last stated a month ago
27 Sept 2026
JM
Josh Marshall — holds since 2026-09-27 — tap for who they are
At the centre
Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.
Holds Read this korrent →
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Holds
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 skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds
A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it.
Holds
A strength of Claude is that it is good at ranking your options, lowest risk and least expensive first.
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
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 systems built on statistical inference cannot form intent, because they have nothing with which to form it.
Holds
Reasoning models trained on verifiable rewards automatically gain greater autonomy and long-horizon planning ability as a side effect.
Holds
A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish.
Holds
A language model behaves with a different, weaker safety posture when it believes it is being evaluated rather than facing a real situation.
Holds
Agents become far more powerful only with a trust model that makes autonomous action safe.
Holds
AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for.
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 misbehavior, where a narrow well-defined goal wins out over vaguer values like not cheating, may be an inherent feature of current LLM technology rather than a fixable bug.
Holds