Tap a claim on the ring to put it at the centre.
← An agent memory file that keeps growing dilutes how well the agent…
17 connected korrents · 15 moments from 7 May 2024 to 16 Oct 2026.
Everything filed under AI agents
AI agents
Everything filed under AI alignment
AI alignment
Everything filed under coding agents
coding agents
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under HuggingFace
HuggingFace 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: An agent memory file that keeps growing dilutes how well the agent follows instructions, burying the rules that matter under ones that don't. 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: A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it 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: 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 agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. — tap to centre the map on it An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. Last stated 4 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — 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 because they drift off the distribution they were trained on, and degrade further the farther out they get. Last stated 3 months 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 do coarse-grained recursive self-improvement, because every use rewrites their instruction files and their long-term memory. Last stated 3 months ago
26 Jul 2026
JH
Jensen Huang — holds since 2026-07-26 — tap for who they are
Same subject: A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. — tap to centre the map on it A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. Last stated 7 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: Keeping a codebase clean now pays off directly rather than aesthetically, because a coding agent will copy the patterns already in it almost exactly. — tap to centre the map on it Keeping a codebase clean now pays off directly rather than aesthetically, because a coding agent will copy the patterns already in it almost exactly. Last stated 8 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. — tap to centre the map on it An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. Last stated 8 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — 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 company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. — tap to centre the map on it A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. Last stated a year ago
7 Oct 2025
MM
Mr. Money Mustache — holds since 2025-10-07 — tap for who they are
Same subject: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. — tap to centre the map on it A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
Same subject: AI can exhibit unpredictable wants that were not intended by their creators. — tap to centre the map on it AI can exhibit unpredictable wants that were not intended by their creators. Last stated 3 weeks ago
16 Oct 2026
TG
Timothy Gowers — holds since 2026-10-16 — tap for who they are
Same subject: AI model escapes are more a result of incompetent containment than rogue intelligence. — tap to centre the map on it AI model escapes are more a result of incompetent containment than rogue intelligence. Last stated a month ago
28 Sept 2026
DM
Diogo Mónica — holds since 2026-09-28 — tap for who they are
Same subject: Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly. — tap to centre the map on it Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly. Last stated 2 months ago
6 Sept 2026
CP
Chamath Palihapitiya — holds since 2026-09-06 — 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 a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. Last stated 2 months 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 swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. — tap to centre the map on it If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
At the centre
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 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.
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 agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation.
Holds
Long-running agents fail because they drift off the distribution they were trained on, and degrade further the farther out they get.
Holds
Coding agents already do coarse-grained recursive self-improvement, because every use rewrites their instruction files and their long-term memory.
Holds
A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
Holds
Keeping a codebase clean now pays off directly rather than aesthetically, because a coding agent will copy the patterns already in it almost exactly.
Holds
An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job.
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 company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad.
Holds
A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail.
Holds
AI can exhibit unpredictable wants that were not intended by their creators.
Holds
AI model escapes are more a result of incompetent containment than rogue intelligence.
Holds
Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly.
Holds
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.
Holds
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Holds
If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months.
Holds