korrents

On the map

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

← Every abstraction in agentic programming — RAG, memory, agentic…

17 connected korrents · 15 moments on record from 17 Oct 2025 to 3 Sept 2026.

Everything filed under AI agents AI agents Everything filed under Anthropic Anthropic Everything filed under coding agents coding agents Everything filed under self-sovereign AI self-sovereign AI Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Every abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them. Every abstraction in agentic programming —RAG, memory, agentic history, structuredoutput — is just a different way ofpassing tokens into a model, andunderstanding that beats learning any ofthem. Last stated 2 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: Rust may be the best language for AI agents to write, because the compiler gives an agent the feedback that tells it what to fix. — tap to centre the map on it Rust may be the best language for AIagents to write, because thecompiler gives an agent the feedbackthat tells it what to fix. Last stated 4 months ago 20 May 2026 AR Alice Ryhl — holds since 2026-05-20 — tap for who they are Same subject: The code today’s models and agents write is very hard to follow: you get better performance without knowing why, and no way to fix it when it breaks. — tap to centre the map on it The code today’s models and agentswrite is very hard to follow: youget better performance withoutknowing why, and no way to fix itwhen it breaks. Last stated 2 months ago 19 Jul 2026 ES Elizabeth Stone — holds since 2026-07-19 — tap for who they are Same subject: What limits you with coding agents is your own skill at stringing them together, not the capability of the models. — tap to centre the map on it What limits you with coding agentsis your own skill at stringing themtogether, not the capability of themodels. Last stated 6 months ago 20 Mar 2026 AK Andrej Karpathy — holds since 2026-03-20 — tap for who they are Same subject: Computer-use agents had to wait for language models: without pre-trained representations the reward is too sparse to ever learn from. — tap to centre the map on it Computer-use agents had to wait forlanguage models: without pre-trainedrepresentations the reward is toosparse to ever learn from. Last stated 11 months ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: Specifying what you want matters more now that agents write the code than it did when the work went to a human who could ask follow-up questions. — tap to centre the map on it Specifying what you want mattersmore now that agents write the codethan it did when the work went to ahuman who could ask follow-upquestions. Last stated a month ago 30 Jul 2026 JD Jeff Dean — holds since 2026-07-30 — tap for who they are Same subject: There is no accumulated advantage in agentic coding: someone who ignored the whole of the past year could catch up to the frontier in two weeks. — tap to centre the map on it There is no accumulated advantage inagentic coding: someone who ignoredthe whole of the past year couldcatch up to the frontier in twoweeks. Last stated 2 weeks ago 26 Aug 2026 DH David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are Same subject: What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. — tap to centre the map on it What sits in a model's context isfar clearer to it than its trainingdata, which is trillions of tokensstirred into a soup of parameters. Last stated a month ago 30 Jul 2026 JD Jeff Dean — holds since 2026-07-30 — tap for who they are Same subject: Coding agents already do coarse-grained recursive self-improvement, because every use rewrites their instruction files and their long-term memory. — tap to centre the map on it Coding agents already docoarse-grained recursiveself-improvement, because every userewrites their instruction files andtheir long-term memory. Last stated a month ago 26 Jul 2026 JH Jensen Huang — holds since 2026-07-26 — 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: After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. — tap to centre the map on it After pre-training, post-trainingand test-time scaling, the fourthscaling law is agentic: multiplyingAI by spawning agents, and the wholeloop scales on one thing, compute. Last stated 6 months ago 23 Mar 2026 JH Jensen Huang — holds since 2026-03-23 — tap for who they are Same subject: Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing. — tap to centre the map on it Agent autonomy is a capability, nota product direction: what the personis actually trying to do decideswhether more of it helps or ruinsthe thing. Last stated 4 weeks ago 14 Aug 2026 SP Sunil Pai — holds since 2026-08-14 — 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 Codelast while it stays first in use ismeasuring the wrong thing, and hasbeen for a year. Last stated 5 days 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 summarizeits own system prompt risks thatprompt's content biasing the summaryit produces. Last stated 6 days 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 missionprotects a company better thanfounder control does, which is whyAnthropic needs no dual-classshares. Last stated 4 months ago 10 May 2026 ER Eric Ries — holds since 2026-05-10 — 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 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 on record holding the claim — tap it for who they are

At the centre Every abstraction in agentic programming — RAG, memory, agentic history, structured output — is just a different way of passing tokens into a model, and understanding that beats learning any of them. Last stated 15 Jul 2026 · 2 months ago Holds Dex Horthy Read this korrent →