Tap a claim on the ring to put it at the centre.
← A project-level agent memory file works like a neural net, steering…
17 connected korrents · 15 moments from 10 Dec 2015 to 25 Oct 2026.
Everything filed under AI agents
AI agents
Everything filed under neural networks
neural networks
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. Last stated 2 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — tap for who they are
Same subject: An agent memory file that keeps growing dilutes how well the agent follows instructions, burying the rules that matter under ones that don't. — tap to centre the map on it An agent memory file that keeps growing dilutes how well the agent follows instructions, burying the rules that matter under ones that don't. Last stated 2 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — tap for who they are
Same subject: 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. — tap to centre the map on it 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 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: AI coding agents work best with the same general-purpose tools built for humans, such as git and file utilities, rather than agent-specific interfaces. — tap to centre the map on it AI coding agents work best with the same general-purpose tools built for humans, such as git and file utilities, rather than agent-specific interfaces. Last stated a year ago
30 Sept 2025
HR
Harper Reed — holds since 2025-09-30 — tap for who they are
Same subject: Storing an AI agent's memory as files forces it to compress what it learns into a form that survives even when the conversation itself doesn't. — tap to centre the map on it Storing an AI agent's memory as files forces it to compress what it learns into a form that survives even when the conversation itself doesn't. Last stated 6 months ago
10 May 2026
JL
Jason Liu — holds since 2026-05-10 — tap for who they are
Same subject: An AI agent is essentially just an LLM, a set of tools, and a loop, not a complicated framework. — tap to centre the map on it An AI agent is essentially just an LLM, a set of tools, and a loop, not a complicated framework. Last stated 3 months ago
14 Aug 2026
AM
Amit Merchant — holds since 2026-08-14 — tap for who they are
Same subject: Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents. — tap to centre the map on it Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents. Last stated a week ago
25 Oct 2026
TB
Thorsten Ball — holds since 2026-10-25 — tap for who they are
Same subject: Agentic code search has recall that falls as a codebase grows, so the agent does not find the code it needs -- and which search tool you give it barely matters. — tap to centre the map on it Agentic code search has recall that falls as a codebase grows, so the agent does not find the code it needs -- and which search tool you give it barely matters. Last stated 7 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: Locality is what makes a language good for AI: if a single file states what it imports and what it offers, a model never has to hold the whole program at once. — tap to centre the map on it Locality is what makes a language good for AI: if a single file states what it imports and what it offers, a model never has to hold the whole program at once. Last stated 6 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — 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 with reference to its own input rather than an unreferenced function, which is 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 small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on it A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. 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: A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. — tap to centre the map on it A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. Last stated 9 years ago
12 Jun 2017
IP
Illia Polosukhin — holds since 2017-06-12 — tap for who they are
JU
Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are
NP
Niki Parmar — holds since 2017-06-12 — tap for who they are
AV
Ashish Vaswani — holds since 2017-06-12 — tap for who they are
NS
Noam Shazeer — holds since 2017-06-12 — tap for who they are
AG
Aidan N. Gomez — holds since 2017-06-12 — tap for who they are
+2
2 more
Same subject: Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. — tap to centre the map on it Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. Last stated 3 years ago
24 Jun 2023
YB
Yoshua Bengio — holds since 2023-06-24 — tap for who they are
Same subject: We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them. — tap to centre the map on it We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them. Last stated 4 years ago
17 Feb 2023
AR
Armin Ronacher — holds since 2023-02-17 — tap for who they are
Same subject: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. Last stated 4 weeks ago
9 Oct 2026
CR
Carl Rivera — holds since 2026-10-09 — tap for who they are
Same subject: A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. — tap to centre the map on it A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. 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: Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. — tap to centre the map on it Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. Last stated 5 years ago
11 Jun 2021
GW
Gwern — holds since 2021-06-11 — tap for who they are
Same subject: Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free. — tap to centre the map on it Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free. 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
At the centre
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Holds Read this korrent →
An agent memory file that keeps growing dilutes how well the agent follows instructions, burying the rules that matter under ones that don't.
Holds
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.
Holds
AI coding agents work best with the same general-purpose tools built for humans, such as git and file utilities, rather than agent-specific interfaces.
Holds
Storing an AI agent's memory as files forces it to compress what it learns into a form that survives even when the conversation itself doesn't.
Holds
An AI agent is essentially just an LLM, a set of tools, and a loop, not a complicated framework.
Holds
Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents.
Holds
Agentic code search has recall that falls as a codebase grows, so the agent does not find the code it needs -- and which search tool you give it barely matters.
Holds
Locality is what makes a language good for AI: if a single file states what it imports and what it offers, a model never has to hold the whole program at once.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds
A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.
Holds
Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source.
Holds
We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them.
Holds
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Holds
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Holds
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Holds
Pruning cuts the parameters of a trained network by over 90% without costing accuracy, so inference gets smaller and faster for free.
Holds