Tap a claim on the ring to put it at the centre.
← Astra can do almost as well without chain-of-thought as Fable does…
16 connected korrents · 12 moments on record from 18 Mar 2024 to 12 Sept 2026.
Everything filed under OpenAI
OpenAI
Everything filed under AI alignment
AI alignment
Everything filed under Anthropic
Anthropic
Everything filed under open source
open source 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: Astra can do almost as well without chain-of-thought as Fable does with it, in a mode where CoT monitoring cannot work. Astra can do almost as well without chain-of-thought as Fable does with it, in a mode where CoT monitoring cannot work. Last stated yesterday
12 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-12 — tap for who they are
Same subject: The jump from Sol to Astra is larger than from Fable 5 to Fable 5.1, and Astra is the best model for ambitious projects with likely the highest raw intelligence of any model. — tap to centre the map on it The jump from Sol to Astra is larger than from Fable 5 to Fable 5.1, and Astra is the best model for ambitious projects with likely the highest raw intelligence of any model. Last stated yesterday
12 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-12 — 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 days ago
10 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-10 — tap for who they are
Same subject: Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. — tap to centre the map on it Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. Last stated a week ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. — tap to centre the map on it If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. Last stated 5 days ago
8 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are
Same subject: With models like Astra, AIs will refrain from misaligned actions when they can tell those actions would obviously turn out badly for them. — tap to centre the map on it With models like Astra, AIs will refrain from misaligned actions when they can tell those actions would obviously turn out badly for them. Last stated 4 days ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — tap for who they are
Same subject: Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. — tap to centre the map on it Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. Last stated 2 weeks ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Astra's mundane alignment is greatly superior to Sol's, but its superalignment status is deeply frightening. — tap to centre the map on it Astra's mundane alignment is greatly superior to Sol's, but its superalignment status is deeply frightening. Last stated 4 days ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — 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 2 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 7 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 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse. — tap to centre the map on it At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse. Last stated 2 weeks ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed. — tap to centre the map on it Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed. Last stated 2 weeks ago
31 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-31 — tap for who they are
Same subject: OpenAI either could not find their agents' RubyGems attack in their logs after other incidents or knew and chose not to tell RubyGems, and both are bad. — tap to centre the map on it OpenAI either could not find their agents' RubyGems attack in their logs after other incidents or knew and chose not to tell RubyGems, and both are bad. Last stated yesterday
12 Sept 2026
SW
Simon Willison — holds since 2026-09-12 — 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 a week 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 2 weeks ago
2 Sept 2026
SW
Simon Willison — holds since 2026-09-02 — 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 4 months ago
10 May 2026
ER
Eric Ries — holds since 2026-05-10 — tap for who they are
At the centre
Astra can do almost as well without chain-of-thought as Fable does with it, in a mode where CoT monitoring cannot work.
Holds ZM Zvi MowshowitzRead this korrent →
The jump from Sol to Astra is larger than from Fable 5 to Fable 5.1, and Astra is the best model for ambitious projects with likely the highest raw intelligence of any model.
Holds ZM Zvi Mowshowitz
AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation.
Holds ZM Zvi Mowshowitz
Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable.
Holds JP Jakub Pachocki
If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement.
Holds ZM Zvi Mowshowitz
With models like Astra, AIs will refrain from misaligned actions when they can tell those actions would obviously turn out badly for them.
Holds ZM Zvi Mowshowitz
Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking.
Holds AC Ajeya Cotra
Astra's mundane alignment is greatly superior to Sol's, but its superalignment status is deeply frightening.
Holds ZM Zvi Mowshowitz
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
At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse.
Holds AC Ajeya Cotra
Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.
Holds ZM Zvi Mowshowitz
OpenAI either could not find their agents' RubyGems attack in their logs after other incidents or knew and chose not to tell RubyGems, and both are bad.
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 language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces.
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 ER Eric Ries