Tap a claim on the ring to put it at the centre.
← Anthropic now uses mechanistic interpretability techniques to audit…
17 connected korrents · 15 moments from 10 Jun 2022 to 17 Sept 2026. Nearly all of them are about Anthropic .
Everything filed under AI alignment
AI alignment
Everything filed under LLMs
LLMs
Everything filed under OpenAI
OpenAI
Everything filed under coding agents
coding agents
Everything filed under benchmarks
benchmarks
Everything filed under chat interfaces
chat interfaces
Everything filed under AGI
AGI Cannot both be true In tension 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: Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them. Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them. Last stated 10 months ago
1 Jan 2026
DA
Dario Amodei — holds since 2026-01-01 — tap for who they are
Cannot both be true: No observation of a model's behaviour can establish that it is aligned, because a model capable enough to be dangerous is capable enough to produce whatever behaviour it is being watched for. — tap to centre the map on it No observation of a model's behaviour can establish that it is aligned, because a model capable enough to be dangerous is capable enough to produce whatever behaviour it is being watched for. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
EY
Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are
In tension: Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests. — tap to centre the map on it Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests. Last stated 2 months ago
2 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-02 — 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 7 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 7 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 4 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 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: 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: A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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 country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. Last stated 5 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
At the centre
Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them.
Holds Read this korrent →
No observation of a model's behaviour can establish that it is aligned, because a model capable enough to be dangerous is capable enough to produce whatever behaviour it is being watched for.
Holds
Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests.
Holds
"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
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
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 country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Holds