korrents

On the map

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

← Making an agent somewhat durable is not very hard, but making an agent…

17 connected korrents · 17 moments from 20 Dec 2024 to 29 Oct 2026.

Everything filed under AI agents AI agents Everything filed under AI alignment AI alignment Everything filed under innovation innovation Everything filed under pruning pruning Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Making an agent somewhat durable is not very hard, but making an agent harness inherently durable without it becoming a mess is surprisingly hard. Making an agent somewhat durable is notvery hard, but making an agent harnessinherently durable without it becoming amess is surprisingly hard. Last stated 2 months ago 4 Oct 2026 AR Armin Ronacher — holds since 2026-10-04 — tap for who they are Same subject: An agent harness should be minimal and customizable, because models keep advancing and the harness has to be flexible enough to evolve with them. — tap to centre the map on it An agent harness should be minimaland customizable, because modelskeep advancing and the harness hasto be flexible enough to evolve withthem. Last stated 4 months ago 1 Aug 2026 KC Kun Chen — holds since 2026-08-01 — tap for who they are Same subject: How well the harness is built makes a huge difference to agentic system performance; research shows the same model performing up to six times better with a better harness. — tap to centre the map on it How well the harness is built makesa huge difference to agentic systemperformance; research shows the samemodel performing up to six timesbetter with a better harness. Last stated 3 weeks ago 29 Oct 2026 AR Aishwarya Naresh Reganti — holds since 2026-10-29 — tap for who they are Same subject: The more capable an agent is made, the more it can do on its own without the person shuttling context to it. — tap to centre the map on it The more capable an agent is made,the more it can do on its ownwithout the person shuttling contextto it. Last stated 2 months ago 15 Sept 2026 KD Kent C. Dodds — holds since 2026-09-15 — tap for who they are Same subject: Making a product work for agents is probably largely a matter of building the right primitives into it, almost as an infrastructural layer. — tap to centre the map on it Making a product work for agents isprobably largely a matter ofbuilding the right primitives intoit, almost as an infrastructurallayer. Last stated 2 months ago 10 Sept 2026 MK Mike Krieger — holds since 2026-09-10 — tap for who they are Same subject: Agent harnesses are only at the beginning, with probably a lot more innovation still to come. — tap to centre the map on it Agent harnesses are only at thebeginning, with probably a lot moreinnovation still to come. Last stated 4 months ago 30 Jul 2026 BV Ben Vinegar — holds since 2026-07-30 — tap for who they are Same subject: Being more intentional about what agents are able to do reduces the chances of catastrophe. — tap to centre the map on it Being more intentional about whatagents are able to do reduces thechances of catastrophe. Last stated 2 months ago 15 Sept 2026 KD Kent C. Dodds — holds since 2026-09-15 — tap for who they are Same subject: Most agent harnesses need some pruning during context compaction anyway for cost reasons, which Jev might help with. — tap to centre the map on it Most agent harnesses need somepruning during context compactionanyway for cost reasons, which Jevmight help with. Last stated 2 months ago 18 Sept 2026 AR Armin Ronacher — holds since 2026-09-18 — tap for who they are Same subject: The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart. — tap to centre the map on it The winning move in coding agentswas inverted: take share with amerely good-enough harness first,then go back and make the harnesssmart. Last stated 6 months ago 27 May 2026 DR Dax Raad — holds since 2026-05-27 — 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 lacka huge amount of knowledge and relyon continual learning instead, socontinual learning is whatsuperintelligence should mean. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. — tap to centre the map on it A proposal to pace frontier AIdevelopment is unrealistic andmainly serves political control ofAI. Last stated 2 months ago 18 Sept 2026 BT Ben Thompson — holds since 2026-09-18 — tap for who they are Same subject: Abstract talk of AGI and superintelligence is too abstract; AI has to actually work. — tap to centre the map on it Abstract talk of AGI andsuperintelligence is too abstract;AI has to actually work. Last stated 2 years ago 26 Jan 2025 MA Marc Andreessen — holds since 2025-01-26 — tap for who they are Same subject: Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us. — tap to centre the map on it Adapting over time is a workableanswer to humans misusing AI and noanswer at all to losing control ofsystems smarter than us. Last stated 2 years ago 5 Apr 2025 HT Helen Toner — holds since 2025-04-05 — tap for who they are Same subject: Advanced AI is close enough that the preparations which take years have to be started now, whichever end of the expert range you believe. — tap to centre the map on it Advanced AI is close enough that thepreparations which take years haveto be started now, whichever end ofthe expert range you believe. Last stated 2 years ago 1 Apr 2025 HT Helen Toner — holds since 2025-04-01 — tap for who they are MB Miles Brundage — holds since 2024-12-20 — tap for who they are Same subject: AI loss-of-control risk could materialize within years, not decades — tap to centre the map on it AI loss-of-control risk couldmaterialize within years, notdecades Last stated 4 months ago 16 Jul 2026 MB Miles Brundage — holds since 2026-07-16 — tap for who they are Same subject: AIs, like children raised in a culture, can eventually be guided through teaching to join civilization rather than requiring permanent control. — tap to centre the map on it AIs, like children raised in aculture, can eventually be guidedthrough teaching to joincivilization rather than requiringpermanent control. Last stated 2 months ago 25 Sept 2026 RH Robin Hanson — holds since 2026-09-25 — tap for who they are Same subject: Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. — tap to centre the map on it Alignment of today's models is goingwell enough to look solvable, whilealigning models we can no longerunderstand remains unsolved. Last stated 10 months ago 22 Jan 2026 JL Jan Leike — holds since 2026-01-22 — tap for who they are Same subject: A base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another. — tap to centre the map on it A base model learns humanity'scollective knowledge, and it thenhas to be aligned to behave one wayor another. Last stated a year ago 10 Sept 2025 SA Sam Altman — holds since 2025-09-10 — 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 Making an agent somewhat durable is not very hard, but making an agent harness inherently durable without it becoming a mess is surprisingly hard. Last stated 4 Oct 2026 · 2 months ago Holds Armin Ronacher Read this korrent →