Tap a claim on the ring to put it at the centre.
← Giving LLMs explicit instructions, rather than assuming alignment,…
17 connected korrents · 18 moments on record from 24 Oct 2017 to 15 Sept 2026. Nearly all of them are about AI alignment .
Everything filed under LLMs
LLMs
Everything filed under AGI
AGI
Everything filed under consciousness
consciousness 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: Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems. Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems. Last stated 3 months ago
15 Jun 2026
RK
Rohit Krishnan — holds since 2026-06-15 — tap for who they are
Same subject: Whether advanced AI poses an existential risk to humanity is currently unknowable. — tap to centre the map on it Whether advanced AI poses an existential risk to humanity is currently unknowable. Last stated 6 days ago
15 Sept 2026
MS
M.G. Siegler — holds since 2026-09-15 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 10 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. — tap to centre the map on it A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. Last stated 2 weeks ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — tap for who they are
Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. Last stated 9 years ago
24 Oct 2017
ÉT
Émile P. Torres — holds since 2017-10-24 — tap for who they are
Same subject: A validated theory of intelligence may be necessary for achieving genuine AI alignment. — tap to centre the map on it A validated theory of intelligence may be necessary for achieving genuine AI alignment. Last stated a month ago
17 Aug 2026
KK
Kevin Kelly — holds since 2026-08-17 — tap for who they are
Same subject: AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual. — tap to centre the map on it AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual. Last stated a month ago
21 Aug 2026
RK
Rohit Krishnan — holds since 2026-08-21 — tap for who they are
Same subject: AI companies are conflicted messengers when warning about AI safety risks, given their own marketing and regulatory incentives. — tap to centre the map on it AI companies are conflicted messengers when warning about AI safety risks, given their own marketing and regulatory incentives. Last stated a week ago
11 Sept 2026
CN
Casey Newton — holds since 2026-09-11 — tap for who they are
Same subject: AI researchers are overly focused on risks from model misalignment relative to risks arising from other layers of the AI stack. — tap to centre the map on it AI researchers are overly focused on risks from model misalignment relative to risks arising from other layers of the AI stack. Last stated 7 months ago
28 Feb 2026
JS
Jasmine Sun — holds since 2026-02-28 — 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 9 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 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. — tap to centre the map on it A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. Last stated a month ago
10 Aug 2026
FL
Fei-Fei Li — holds since 2026-08-10 — tap for who they are
Same subject: Humans can generally perform new language tasks from few examples or simple instructions, while current NLP systems largely cannot. — tap to centre the map on it Humans can generally perform new language tasks from few examples or simple instructions, while current NLP systems largely cannot. Last stated 6 years ago
28 May 2020
DA
Dario Amodei — holds since 2020-05-28 — tap for who they are
Same subject: Language models are already a form of AGI; what the labs are chasing is a further step, not the arrival of general intelligence. — tap to centre the map on it Language models are already a form of AGI; what the labs are chasing is a further step, not the arrival of general intelligence. Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — 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 a week ago
12 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-12 — 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: LLMs replacing podcasts as a source of information poses a real disruption to podcasting. — tap to centre the map on it LLMs replacing podcasts as a source of information poses a real disruption to podcasting. Last stated 3 months ago
25 Jun 2026
JJ
Justin Jackson — holds since 2026-06-25 — tap for who they are
Same subject: The frontier labs optimise their models for code above everything else because coding is where the money is: developers will pay $200 a month once a model is good enough. — tap to centre the map on it The frontier labs optimise their models for code above everything else because coding is where the money is: developers will pay $200 a month once a model is good enough. Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
At the centre
Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.
Holds Read this korrent →
Whether advanced AI poses an existential risk to humanity is currently unknowable.
Holds
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Holds
A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety.
Holds
A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough.
Holds
A validated theory of intelligence may be necessary for achieving genuine AI alignment.
Holds
AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual.
Holds
AI companies are conflicted messengers when warning about AI safety risks, given their own marketing and regulatory incentives.
Holds
AI researchers are overly focused on risks from model misalignment relative to risks arising from other layers of the AI stack.
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 child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved.
Holds
Humans can generally perform new language tasks from few examples or simple instructions, while current NLP systems largely cannot.
Holds
Language models are already a form of AGI; what the labs are chasing is a further step, not the arrival of general intelligence.
Holds
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
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
LLMs replacing podcasts as a source of information poses a real disruption to podcasting.
Holds
The frontier labs optimise their models for code above everything else because coding is where the money is: developers will pay $200 a month once a model is good enough.
Holds