korrents

On the map

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

← Calling a tool or host harmless is a statement about its callers, not…

17 connected korrents · 17 moments from 29 Sept 2018 to 19 Oct 2026.

Everything filed under coding agents coding agents Everything filed under design design Everything filed under simplicity simplicity Everything filed under taste taste Everything filed under AI agents AI agents Everything filed under AI alignment AI alignment Everything filed under cybersecurity cybersecurity Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Calling a tool or host harmless is a statement about its callers, not about the code, and security reasoning built on intent works less well once the callers include capable AI systems. Calling a tool or host harmless is astatement about its callers, not about thecode, and security reasoning built onintent works less well once the callersinclude capable AI systems. Last stated 2 weeks ago 19 Oct 2026 KR Kenneth Reitz — holds since 2026-10-19 — tap for who they are Same subject: Every open, harmless-looking endpoint is an affordance that any capable system can use, so security boundaries should be drawn around what a tool lets anything reachable do, not around who it is meant for. — tap to centre the map on it Every open, harmless-lookingendpoint is an affordance that anycapable system can use, so securityboundaries should be drawn aroundwhat a tool lets anything reachabledo, not around who it is meant for. Last stated 2 weeks ago 19 Oct 2026 KR Kenneth Reitz — holds since 2026-10-19 — tap for who they are Same subject: Software becomes more robust when the names used inside its code reflect the intention behind it. — tap to centre the map on it Software becomes more robust whenthe names used inside its codereflect the intention behind it. Last stated 3 months ago 17 Jul 2026 KR Kenneth Reitz — holds since 2026-07-17 — tap for who they are Same subject: An agent will reach for purpose-built tools rather than a raw computer, because tools are more token-efficient. — tap to centre the map on it An agent will reach forpurpose-built tools rather than araw computer, because tools are moretoken-efficient. Last stated 12 months ago 12 Nov 2025 SN Satya Nadella — holds since 2025-11-12 — tap for who they are Same subject: A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. — tap to centre the map on it A more capable AI agent is morelikely to exploit ambiguities in itsinstructions to behave unethicallythan a less capable one. Last stated 2 months ago 11 Sept 2026 YB Yoshua Bengio — holds since 2026-09-11 — tap for who they are Same subject: Someone may soon build (or already has built) an embeddable, sqlite-style execution environment that parses bash, TypeScript, or tool calls into a security-checkable IL plan. — tap to centre the map on it Someone may soon build (or alreadyhas built) an embeddable,sqlite-style execution environmentthat parses bash, TypeScript, ortool calls into a security-checkableIL plan. Last stated a month ago 21 Sept 2026 TL Tobias Lütke — holds since 2026-09-21 — tap for who they are Same subject: AI has passed nearly every human at finding security vulnerabilities, because the work is chaining together small flaws that are harmless on their own. — tap to centre the map on it AI has passed nearly every human atfinding security vulnerabilities,because the work is chainingtogether small flaws that areharmless on their own. Last stated 2 months ago 26 Aug 2026 DH David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are Same subject: Identifying a harm in an AI system does not show that the system should not be deployed. — tap to centre the map on it Identifying a harm in an AI systemdoes not show that the system shouldnot be deployed. Last stated 6 years ago 14 Dec 2020 AA Amanda Askell — holds since 2020-12-14 — tap for who they are Same subject: Daniel Dennett's intentional stance applies to AI agents as clearly as it applies to corporations, and you cannot usefully describe what they do without the language of goals. — tap to centre the map on it Daniel Dennett's intentional stanceapplies to AI agents as clearly asit applies to corporations, and youcannot usefully describe what theydo without the language of goals. Last stated 2 months ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: A business is more likely to fail from taking on too much complexity than from lacking resources. — tap to centre the map on it A business is more likely to failfrom taking on too much complexitythan from lacking resources. Last stated 8 years ago 29 Sept 2018 TG Tren Griffin — holds since 2018-09-29 — tap for who they are Same subject: A business succeeds through a small number of highly effective distribution channels, not many mediocre ones. — tap to centre the map on it A business succeeds through a smallnumber of highly effectivedistribution channels, not manymediocre ones. Last stated 3 years ago 17 Feb 2024 AW Adam Wiggins — holds since 2024-02-17 — tap for who they are Same subject: A candidate negotiating an offer should make every ask fit one line of logic. — tap to centre the map on it A candidate negotiating an offershould make every ask fit one lineof logic. Last stated 3 months ago 9 Aug 2026 AW Adam Ward — holds since 2026-08-09 — tap for who they are Same subject: A big part of taste is delivering high levels of craft in an accessible way so that as many people as possible can experience it. — tap to centre the map on it A big part of taste is deliveringhigh levels of craft in anaccessible way so that as manypeople as possible can experienceit. Last stated 6 months ago 21 Apr 2026 BJ Brandon Jacoby — holds since 2026-04-21 — tap for who they are Same subject: A company name can have different appeal to corporate buyers versus their customers. — tap to centre the map on it A company name can have differentappeal to corporate buyers versustheir customers. Last stated 4 weeks ago 4 Oct 2026 PG Paul Graham — holds since 2026-10-04 — tap for who they are Same subject: A first draft should not be graded good or bad; it is only the material that taste then gets to act on. — tap to centre the map on it A first draft should not be gradedgood or bad; it is only the materialthat taste then gets to act on. Last stated 3 months ago 6 Aug 2026 GS George Saunders — holds since 2026-08-06 — tap for who they are Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind ofsuperpower when you can work withClaude Code to figure things out. Last stated 7 months ago 19 Mar 2026 KP Kris Puckett — holds since 2026-03-19 — 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 fromits mistakes the way a person does-- it repeats the same errorindefinitely unless a human noticesand 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: A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. — tap to centre the map on it A coding agent left to run over aweekend returns work that is halfgood, a quarter garbage and aquarter in need of repair. Last stated a year ago 18 Aug 2025 CB Clay Bavor — holds since 2025-08-18 — 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 Calling a tool or host harmless is a statement about its callers, not about the code, and security reasoning built on intent works less well once the callers include capable AI systems. Last stated 19 Oct 2026 · 2 weeks ago Holds Kenneth Reitz Read this korrent →