korrents

On the map

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

← Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays.

15 connected korrents · 12 moments on record from 1 Nov 1997 to 4 Sept 2026.

Everything filed under AI agents AI agents Everything filed under self-sovereign AI self-sovereign AI Everything filed under neural networks neural networks Everything filed under pruning pruning Everything filed under AI and science AI and science Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays. Recurrent backpropagation learns slowlyover long intervals mainly because errorbackflow decays. Last stated 29 years ago 1 Nov 1997 JS Jürgen Schmidhuber — holds since 1997-11-01 — tap for who they are SH Sepp Hochreiter — holds since 1997-11-01 — tap for who they are Same subject: Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get. — tap to centre the map on it Long-running agents fail becausethey drift off the distribution theywere trained on, and degrade furtherthe farther out they get. Last stated a month ago 30 Jul 2026 JD Jeff Dean — holds since 2026-07-30 — tap for who they are Same subject: Anything nature shaped can be learned efficiently by a classical neural network, because evolutionary processes leave structure behind. — tap to centre the map on it Anything nature shaped can belearned efficiently by a classicalneural network, because evolutionaryprocesses leave structure behind. Last stated a year ago 23 Jul 2025 DH Demis Hassabis — holds since 2025-07-23 — tap for who they are Same subject: The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. — tap to centre the map on it The knowledge a model soaks up inpre-training is holding it back;what we actually want is theintelligence with the knowledgestripped out. Last stated 11 months ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start. — tap to centre the map on it The saving pruning offers is onlyever at inference, because thesparse architectures it produces arehard to train from the start. Last stated 9 years ago 9 Mar 2018 MC Michael Carbin — holds since 2018-03-09 — tap for who they are JF Jonathan Frankle — holds since 2018-03-09 — tap for who they are Same subject: Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. — tap to centre the map on it Learned approximations of slowsimulators change what science ispossible, by turning a six-monthscreening run into something you doover lunch. Last stated a month ago 30 Jul 2026 JD Jeff Dean — holds since 2026-07-30 — tap for who they are Same subject: Learning from a reward ten years away is a solved problem: a value function trained by temporal-difference learning rewards the steps along the way. — tap to centre the map on it Learning from a reward ten yearsaway is a solved problem: a valuefunction trained bytemporal-difference learning rewardsthe steps along the way. Last stated 11 months ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — tap for who they are Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs amachine of its own, or you willspend the day fighting it for themouse cursor. Last stated a month ago 10 Aug 2026 PS Peter Steinberger — holds since 2026-08-10 — tap for who they are Same subject: A future where agents run and improve an organisation is impossible unless humans can first see and understand the system themselves. — tap to centre the map on it A future where agents run andimprove an organisation isimpossible unless humans can firstsee and understand the systemthemselves. Last stated 6 months ago 22 Mar 2026 NF Nicole Forsgren — holds since 2026-03-22 — tap for who they are Same subject: A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. — tap to centre the map on it A handful of AI agents is not ahandful of colleagues, becauseagents agree with you constantly andcolleagues tell you where you arewrong. Last stated 6 months ago 22 Mar 2026 NF Nicole Forsgren — holds since 2026-03-22 — tap for who they are Same subject: A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. — tap to centre the map on it A rogue deployment that gets afoothold can hitch a ride on theintelligence explosion, recruitingeach new model as it comes off thepresses. Last stated a week ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. — tap to centre the map on it A slightly more capable agent swarmhas a very strong incentive to setup a wholly unmonitored roguedeployment of itself. Last stated a week ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. — tap to centre the map on it Alignment is no solution toself-sovereign AI, because it is anunsolved problem whose answerscannot be imposed on every AIcompany on Earth. Last stated a week ago 1 Sept 2026 DB Dean W. Ball — holds since 2026-09-01 — tap for who they are Same subject: Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. — tap to centre the map on it Auto-mode does not yet convincinglyfix prompt-injection risk for codingagents. Last stated a month ago 8 Aug 2026 SW Simon Willison — holds since 2026-08-08 — tap for who they are Same subject: Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks. — tap to centre the map on it Current prompt-injection defensesfor AI agents (such as auto mode)are now reliable enough that agentscan practically be assumed safe fromsuccessful injection attacks. Last stated 6 days ago 4 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-04 — tap for who they are Same subject: Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject. — tap to centre the map on it Do not run a personal agent on acheap or local model: weak modelsare gullible and easy toprompt-inject. Last stated 7 months ago 12 Feb 2026 PS Peter Steinberger — holds since 2026-02-12 — 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 1997 to today (stretched back to the oldest claim here) — full is todaya face: someone on record holding the claim — tap it for who they are

At the centre Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays. Last stated 1 Nov 1997 · 29 years ago Holds Jürgen SchmidhuberSepp Hochreiter Read this korrent →