Tap a claim on the ring to put it at the centre.
← All compression of an agent's context is lossy, so compaction needs an algorithm that keeps the important details.
17 connected korrents · 18 moments from 15 Apr 2022 to 3 Nov 2026.
Everything filed under AI agents
AI agents
Everything filed under AI alignment
AI alignment
Everything filed under cybersecurity
cybersecurity
Everything filed under coding agents
coding agents
Everything filed under LLMs
LLMs
Everything filed under pruning
pruning
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: All compression of an agent's context is lossy, so compaction needs an algorithm that keeps the important details.
All compression of an agent's context is lossy, so compaction needs an algorithm that keeps the important details.
Last stated a month ago
11 Oct 2026
LR
Lee Robinson — holds since 2026-10-11 — tap for who they are
Same subject: Any LLM system that uses compaction needs to preserve the pre-compacted text and make it available via agent tool calls. — tap to centre the map on it
Any LLM system that uses compaction needs to preserve the pre-compacted text and make it available via agent tool calls.
Last stated 2 months ago
12 Sept 2026
SW
Simon Willison — holds since 2026-09-12 — tap for who they are
Same subject: Stop managing an agent's context by hand: compaction works very well, so keep one thread per task. — tap to centre the map on it
Stop managing an agent's context by hand: compaction works very well, so keep one thread per task.
Last stated 4 weeks ago
25 Oct 2026
TB
Thorsten Ball — holds since 2026-10-25 — 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 some pruning during context compaction anyway for cost reasons, which Jev might 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: If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context. — tap to centre the map on it
If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context.
Last stated 6 months ago
3 Jun 2026
KH
Kelsey Hightower — holds since 2026-06-03 — 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: If people cannot agree on what words mean, it is hard to expect an agent to understand an instruction completely and carry it out precisely. — tap to centre the map on it
If people cannot agree on what words mean, it is hard to expect an agent to understand an instruction completely and carry it out precisely.
Last stated 3 months ago
25 Aug 2026
NE
NeetCode — holds since 2026-08-25 — tap for who they are
Same subject: A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble. — tap to centre the map on it
A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble.
Last stated 3 weeks ago
3 Nov 2026
DB
Derek Briggs — holds since 2026-11-03 — tap for who they are
Same subject: With coding agents, working out the shape in lower-fidelity mock-ups first beats having the agent build it and then fixing the code: it takes fewer tokens and puts you on a better path. — tap to centre the map on it
With coding agents, working out the shape in lower-fidelity mock-ups first beats having the agent build it and then fixing the code: it takes fewer tokens and puts you on a better path.
Last stated 3 months ago
3 Sept 2026
BV
Ben Vinegar — holds since 2026-09-03 — 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 a month ago
9 Oct 2026
CR
Carl Rivera — holds since 2026-10-09 — tap for who they are
Same subject: A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies. — tap to centre the map on it
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated a year ago
8 Jul 2025
RG
Ryan Greenblatt — holds since 2025-07-08 — 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's collective knowledge, and it then has to be aligned to behave one way or another.
Last stated a year ago
10 Sept 2025
SA
Sam Altman — holds since 2025-09-10 — tap for who they are
Same subject: A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing. — tap to centre the map on it
A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing.
Last stated 5 years ago
15 Apr 2022
TH
Troy Hunt — holds since 2022-04-15 — tap for who they are
Same subject: A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too. — tap to centre the map on it
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Last stated 2 years ago
25 Mar 2025
TH
Troy Hunt — holds since 2025-03-25 — tap for who they are
Same subject: A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root. — tap to centre the map on it
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Last stated 9 months ago
16 Feb 2026
JS
Jon Seager — holds since 2026-02-16 — 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 a month 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 2 months ago
28 Sept 2026
DM
Diogo Mónica — holds since 2026-09-28 — tap for who they are
Same subject: By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group. — tap to centre the map on it
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
Last stated 3 months ago
19 Aug 2026
DT
Derek Thompson — holds since 2026-08-19 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
All compression of an agent's context is lossy, so compaction needs an algorithm that keeps the important details.
Last stated 11 Oct 2026 · a month ago
Holds Lee Robinson
Read this korrent →
Similar wording
Any LLM system that uses compaction needs to preserve the pre-compacted text and make it available via agent tool calls.
Last stated 12 Sept 2026 · 2 months ago
Holds Simon Willison
Similar wording
Stop managing an agent's context by hand: compaction works very well, so keep one thread per task.
Last stated 25 Oct 2026 · 4 weeks ago
Holds Thorsten Ball
Similar wording
Most agent harnesses need some pruning during context compaction anyway for cost reasons, which Jev might help with.
Last stated 18 Sept 2026 · 2 months ago
Holds Armin Ronacher
Similar wording
If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context.
Last stated 3 Jun 2026 · 6 months ago
Holds Kelsey Hightower
Similar wording
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 20 Mar 2026 · 8 months ago
Holds Andrej Karpathy
Similar wording
If people cannot agree on what words mean, it is hard to expect an agent to understand an instruction completely and carry it out precisely.
Last stated 25 Aug 2026 · 3 months ago
Holds NeetCode
Similar wording
A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble.
Last stated 3 Nov 2026 · 3 weeks ago
Holds Derek Briggs
Similar wording
With coding agents, working out the shape in lower-fidelity mock-ups first beats having the agent build it and then fixing the code: it takes fewer tokens and puts you on a better path.
Last stated 3 Sept 2026 · 3 months ago
Holds Ben Vinegar
Same subject: AI alignment
"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 9 Oct 2026 · a month ago
Holds Carl Rivera
Same subject: AI alignment
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated 8 Jul 2025 · a year ago
Holds Ryan Greenblatt
Same subject: AI alignment
A base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another.
Last stated 10 Sept 2025 · a year ago
Holds Sam Altman
Same subject: cybersecurity
A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing.
Last stated 15 Apr 2022 · 5 years ago
Holds Troy Hunt
Same subject: cybersecurity
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Last stated 25 Mar 2025 · 2 years ago
Holds Troy Hunt
Same subject: cybersecurity
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Last stated 16 Feb 2026 · 9 months ago
Holds Jon Seager
Same subject: HuggingFace
AI can exhibit unpredictable wants that were not intended by their creators.
Last stated 16 Oct 2026 · a month ago
Holds Timothy Gowers
Same subject: HuggingFace
AI model escapes are more a result of incompetent containment than rogue intelligence.
Last stated 28 Sept 2026 · 2 months ago
Holds Diogo Mónica
Same subject: HuggingFace
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
Last stated 19 Aug 2026 · 3 months ago
Holds Derek Thompson