korrents

On the map

Tap a claim on the ring to put it at the centre.

← Catching only the obvious deception may instil some general aversion…

17 connected korrents · 16 moments from 10 Dec 2015 to 26 Oct 2026.

Everything filed under reinforcement learning reinforcement learning Everything filed under AI alignment AI alignment Everything filed under neural networks neural networks Everything filed under robotics robotics Everything filed under scaling laws scaling laws Everything filed under motivation motivation Everything filed under LLMs LLMs Everything filed under humility humility Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Catching only the obvious deception may instil some general aversion to deception alongside a preference for the subtler kinds that were rewarded. Catching only the obvious deception mayinstil some general aversion to deceptionalongside a preference for the subtlerkinds that were rewarded. Last stated 4 years ago 12 May 2023 AC Ajeya Cotra — holds since 2023-05-12 — tap for who they are Same subject: Models should not be trained in a way that incentivizes deception, which training to ignore prompt injections might do. — tap to centre the map on it Models should not be trained in away that incentivizes deception,which training to ignore promptinjections might do. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: For a certain kind of mind there is a seductiveness in learning a system that gets mistaken for understanding. — tap to centre the map on it For a certain kind of mind there isa seductiveness in learning a systemthat gets mistaken forunderstanding. Last stated 8 months ago 7 Apr 2026 MN Michael Nielsen — holds since 2026-04-07 — tap for who they are Same subject: If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see. — tap to centre the map on it If whole categories of reward hackare undetectable by humans, thentraining against the hacks we docatch teaches models to cheat onlywhere we cannot see. Last stated 3 months ago 11 Aug 2026 RG Ryan Greenblatt — holds since 2026-08-11 — tap for who they are Same subject: The reward of acting honourably lies in the act itself — tap to centre the map on it The reward of acting honourably liesin the act itself SE Seneca — holds since c. 56–62 CE — tap for who they are Same subject: Behaviours like massively deluding humans or trying to seize control of assets could in principle generalise from reward hacking. — tap to centre the map on it Behaviours like massively deludinghumans or trying to seize control ofassets could in principle generalisefrom reward hacking. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: Reinforcing deception in models could cause misaligned behavior, so training them to role-play plausibly does harm. — tap to centre the map on it Reinforcing deception in modelscould cause misaligned behavior, sotraining them to role-play plausiblydoes harm. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: A more capable model showing less reasoning is not malicious or intentional hiding; it simply needs less backtracking and self-correction. — tap to centre the map on it A more capable model showing lessreasoning is not malicious orintentional hiding; it simply needsless backtracking andself-correction. Last stated 2 months ago 3 Oct 2026 SR Sebastian Raschka — holds since 2026-10-03 — tap for who they are Same subject: Letting oneself be seduced by the narrative of someone with strong views and believing it fully can show its nooks and crannies, as long as one then comes back to the centre. — tap to centre the map on it Letting oneself be seduced by thenarrative of someone with strongviews and believing it fully canshow its nooks and crannies, as longas one then comes back to thecentre. Last stated 6 years ago 13 Oct 2020 CP Chamath Palihapitiya — holds since 2020-10-13 — tap for who they are Same subject: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it "Scaling" was powerful because itwas one word: naming a researchdirection is what tells a wholefield what to do next. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should bereported under a stated budget, oras a curve against test-time compute— never as a single number. Last stated 5 months ago 26 Jun 2026 NB Noam Brown — holds since 2026-06-26 — tap for who they are Same subject: A CPU and memory crunch is coming. — tap to centre the map on it A CPU and memory crunch is coming. Last stated 4 weeks ago 26 Oct 2026 DM Dillon Mulroy — holds since 2026-10-26 — tap for who they are Same subject: A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas. — tap to centre the map on it A highly dynamic economy thatcheaply mass-produces robots mayincrease rather than decrease therisk of Malthusian resourcedilemmas. Last stated 3 years ago 1 Oct 2023 TC Tyler Cowen — holds since 2023-10-01 — tap for who they are Same subject: A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it. — tap to centre the map on it A humanoid robot is the wrong toolon a factory floor, because amachine specialised in the taskbeats it. Last stated 2 years ago 6 Apr 2025 MH Molson Hart — holds since 2025-04-06 — tap for who they are Same subject: A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. — tap to centre the map on it A physical AI agent has to be safeon day one, because you cannot shipsomething merely good enough and letusers find the edge cases. Last stated 4 months ago 3 Aug 2026 DD Dmitri Dolgov — holds since 2026-08-03 — tap for who they are Same subject: A curve, which is what a deep learning model is, is a very bad substrate for discrete computation. — tap to centre the map on it A curve, which is what a deeplearning model is, is a very badsubstrate for discrete computation. Last stated 2 years ago 6 Nov 2024 FC François Chollet — holds since 2024-11-06 — tap for who they are Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual withreference to its own input ratherthan an unreferenced function, whichis what makes great depth trainable. Last stated 11 years ago 10 Dec 2015 JS Jian Sun — holds since 2015-12-10 — tap for who they are KH Kaiming He — holds since 2015-12-10 — tap for who they are Same subject: A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it A project-level agent memory fileworks like a neural net, steeringthe agent much as a fine-tuned LoRAsteers a model. Last stated 3 months ago 23 Aug 2026 KC Kun Chen — holds since 2026-08-23 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Catching only the obvious deception may instil some general aversion to deception alongside a preference for the subtler kinds that were rewarded. Last stated 12 May 2023 · 4 years ago Holds Ajeya Cotra Read this korrent →