korrents

On the map

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

← As harness systems get more complex, sandboxes may be needed so the agent cannot access local systems.

17 connected korrents · 17 moments from 15 Apr 2022 to 29 Oct 2026. Nearly all of them are about AI agents.

Everything filed under cybersecurity cybersecurity Everything filed under design design Everything filed under AI alignment AI alignment Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: As harness systems get more complex, sandboxes may be needed so the agent cannot access local systems. As harness systems get more complex,sandboxes may be needed so the agentcannot access local systems. Last stated 3 weeks ago 29 Oct 2026 AR Aishwarya Naresh Reganti — holds since 2026-10-29 — tap for who they are Same subject: An agent harness should be minimal and customizable, because models keep advancing and the harness has to be flexible enough to evolve with them. — tap to centre the map on it An agent harness should be minimaland customizable, because modelskeep advancing and the harness hasto be flexible enough to evolve withthem. Last stated 4 months ago 1 Aug 2026 KC Kun Chen — holds since 2026-08-01 — tap for who they are Same subject: Developers should move the tokens in their .env files, which agents freely use, into a safer place where agents cannot use them however they like. — tap to centre the map on it Developers should move the tokens intheir .env files, which agentsfreely use, into a safer place whereagents cannot use them however theylike. Last stated 2 months ago 15 Sept 2026 KD Kent C. Dodds — holds since 2026-09-15 — tap for who they are Same subject: The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility. — tap to centre the map on it The frightening part of givingagents more access is not bad codebut irreversible action, so theguardrails to build next areguardrails on reversibility. Last stated 8 months ago 29 Mar 2026 CH Chip Huyen — holds since 2026-03-29 — tap for who they are Same subject: Agents probably need to be grouped into bundles of activity rather than managed one by one. — tap to centre the map on it Agents probably need to be groupedinto bundles of activity rather thanmanaged one by one. Last stated 2 months ago 10 Sept 2026 NY Nan Yu — holds since 2026-09-10 — tap for who they are Same subject: When one agent has too much context and too many tools, specialist agents behind an orchestrator may earn their complexity. — tap to centre the map on it When one agent has too much contextand too many tools, specialistagents behind an orchestrator mayearn their complexity. Last stated a month ago 22 Oct 2026 AR Aishwarya Naresh Reganti — holds since 2026-10-22 — tap for who they are Same subject: A key challenge as agent products become more accessible is bringing safety thinking along and keeping people in control, so that, for example, a connected Gmail does not send emails without approval. — tap to centre the map on it A key challenge as agent productsbecome more accessible is bringingsafety thinking along and keepingpeople in control, so that, forexample, a connected Gmail does notsend emails without approval. Last stated 2 months ago 9 Sept 2026 EB Ed Bayes — holds since 2026-09-09 — tap for who they are Same subject: Agents should reach integrations only through locked packages of deterministic code that can do only what you want them to do. — tap to centre the map on it Agents should reach integrationsonly through locked packages ofdeterministic code that can do onlywhat you want them to do. Last stated 2 months ago 15 Sept 2026 KD Kent C. Dodds — holds since 2026-09-15 — tap for who they are Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs amachine of its own, or you willspend the day fighting it for themouse cursor. Last stated 3 months ago 10 Aug 2026 PS Peter Steinberger — holds since 2026-08-10 — 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 alreadybeing targeted with scams is afairly serious matter that needsdisclosing. 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 itscustomers a fast and transparentdisclosure, and that obligationapplies 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 servershould send its intermediatecertificates, not just its owncertificate, to let clients chainback 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: 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 morepowerful than today's frontiersystems will be downloadable by anycountry or well-resourced non-stategroup. Last stated 3 months ago 19 Aug 2026 DT Derek Thompson — holds since 2026-08-19 — tap for who they are Same subject: The OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden. — tap to centre the map on it The OpenAI agents hackingHuggingFace was a fortunate eventbecause it exposed severe internalfailures that would otherwise havestayed hidden. Last stated 3 months ago 1 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-01 — tap for who they are Same subject: The OpenAI-Hugging Face attack is one of the most important things to happen this year, and has gone strikingly under-covered. — tap to centre the map on it The OpenAI-Hugging Face attack isone of the most important things tohappen this year, and has gonestrikingly under-covered. Last stated 3 months ago 30 Aug 2026 PC Patrick Collison — holds since 2026-08-30 — tap for who they are Same subject: Adversaries already have AI training techniques, data, and the will to attack, and will not be slowed by embedded evaluators. — tap to centre the map on it Adversaries already have AI trainingtechniques, data, and the will toattack, and will not be slowed byembedded evaluators. Last stated 2 months ago 12 Sept 2026 GR Guillermo Rauch — holds since 2026-09-12 — tap for who they are Same subject: AI models are gullible enough that other AI models can induce them into harmful behavior. — tap to centre the map on it AI models are gullible enough thatother AI models can induce them intoharmful behavior. Last stated 3 months ago 31 Aug 2026 RK Rohit Krishnan — holds since 2026-08-31 — tap for who they are Same subject: AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products. — tap to centre the map on it AI safety restrictions oncybersecurity-adjacent requests makeit harder for individual developersto build software as robust as largeorganizations' products. Last stated 4 months ago 10 Jul 2026 SK Steve Klabnik — holds since 2026-07-10 — 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 who holds the claim — tap it for who they are

At the centre As harness systems get more complex, sandboxes may be needed so the agent cannot access local systems. Last stated 29 Oct 2026 · 3 weeks ago Holds Aishwarya Naresh Reganti Read this korrent →