17 connected korrents · 15 moments on record from 17 Oct 2025 to 3 Sept 2026.
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 DHDex Horthy
Read this korrent →
-
Similar wording
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.
Last stated 20 May 2026 · 4 months ago
Holds ARAlice Ryhl
-
Similar wording
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.
Last stated 19 Jul 2026 · 2 months ago
Holds ESElizabeth Stone
-
Similar wording
What limits you with coding agents is your own skill at stringing them together, not the capability of the models.
Last stated 20 Mar 2026 · 6 months ago
Holds
Andrej Karpathy
-
Similar wording
Computer-use agents had to wait for language models: without pre-trained representations the reward is too sparse to ever learn from.
Last stated 17 Oct 2025 · 11 months ago
Holds
Andrej Karpathy
-
Similar wording
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.
Last stated 30 Jul 2026 · a month ago
Holds JDJeff Dean
-
Similar wording
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.
Last stated 26 Aug 2026 · 2 weeks ago
Holds
David Heinemeier Hansson
-
Similar wording
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.
Last stated 30 Jul 2026 · a month ago
Holds JDJeff Dean
-
Similar wording
Coding agents already do coarse-grained recursive self-improvement, because every use rewrites their instruction files and their long-term memory.
Last stated 26 Jul 2026 · a month ago
Holds JHJensen Huang
-
Same subject: AI agents
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.
Last stated 22 Mar 2026 · 6 months ago
Holds NFNicole Forsgren
-
Same subject: AI agents
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.
Last stated 23 Mar 2026 · 6 months ago
Holds JHJensen Huang
-
Same subject: AI agents
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.
Last stated 14 Aug 2026 · 4 weeks ago
Holds
Sunil Pai
-
Same subject: Anthropic
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Last stated 3 Sept 2026 · 5 days ago
Holds
Dax Raad
-
Same subject: Anthropic
A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces.
Last stated 2 Sept 2026 · 6 days ago
Holds
Simon Willison
-
Same subject: Anthropic
A trust that owns the mission protects a company better than founder control does, which is why Anthropic needs no dual-class shares.
Last stated 10 May 2026 · 4 months ago
Holds EREric Ries
-
Same subject: self-sovereign AI
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.
Last stated 1 Sept 2026 · a week ago
Holds ACAjeya Cotra
-
Same subject: self-sovereign AI
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Last stated 1 Sept 2026 · a week ago
Holds ACAjeya Cotra
-
Same subject: self-sovereign AI
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.
Last stated 1 Sept 2026 · a week ago
Holds
Dean W. Ball