korrents

On the map

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

← Loop engineering works exactly as far as verification does: make a…

8 connected korrents · 6 moments on record from 21 Jan 2019 to 30 Jul 2026.

Everything filed under Anthropic Anthropic Everything filed under design design Everything filed under energy energy Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Loop engineering works exactly as far as verification does: make a problem very verifiable and you can treat it as a black box and let the model run. Loop engineering works exactly asfar as verification does: make aproblem very verifiable and you cantreat it as a black box and let themodel run. Last stated 2 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: Verifying a simplified model rather than the real system is worth doing even though the real system will still have bugs, because the bugs you designed in never get built. — tap to centre the map on it Verifying a simplified modelrather than the real system isworth doing even though thereal system will still have… Last stated a month ago 29 Jul 2026 HW Hillel Wayne — holds since 2026-07-29 — tap for who they are Same subject: The skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong. — tap to centre the map on it The skill that matters now isnot prompt engineering butgiving a model a way to verifyits own work, and it is the… Last stated a month ago 27 Jul 2026 BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: Software is not less rigorous than traditional engineering; its record-keeping and automated verification are better than most of that field's. — tap to centre the map on it Software is not less rigorousthan traditional engineering;its record-keeping andautomated verification are… Last stated 6 years ago 20 Jan 2021 HW Hillel Wayne — holds since 2021-01-20 — tap for who they are Same subject: Loops belong on codebase quality, not on shipping the features users want; we read all of the code, because program design is what decides whether a codebase stays changeable. — tap to centre the map on it Loops belong on codebasequality, not on shipping thefeatures users want; we readall of the code, because… Last stated 2 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: Engineers are sceptical of formal methods because they were burned by CASE and UML, sold as miracle solutions and imposed on them regardless of fit. — tap to centre the map on it Engineers are sceptical offormal methods because theywere burned by CASE and UML,sold as miracle solutions and… Last stated a month ago 29 Jul 2026 HW Hillel Wayne — holds since 2026-07-29 — tap for who they are Same subject: The hard part of verification is not proving the code correct but working out what the specification should say. — tap to centre the map on it The hard part of verificationis not proving the codecorrect but working out whatthe specification should say. Last stated 8 years ago 21 Jan 2019 HW Hillel Wayne — holds since 2019-01-21 — tap for who they are Same subject: Nuclear power plants, the standard example of software that must be proved correct, do not care about formal verification: thorough testing is enough for them. — tap to centre the map on it Nuclear power plants, thestandard example of softwarethat must be proved correct,do not care about formal… Last stated a month ago 29 Jul 2026 HW Hillel Wayne — holds since 2026-07-29 — tap for who they are Same subject: Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. — tap to centre the map on it Learned approximations of slowsimulators change what scienceis possible, by turning asix-month screening run into… Last stated a month ago 30 Jul 2026 JD Jeff Dean — holds since 2026-07-30 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: how recently it was last stated — full and dark this week, a faint sliver at five yearsa face: someone on record holding the claim — tap it for who they are

At the centre Loop engineering works exactly as far as verification does: make a problem very verifiable and you can treat it as a black box and let the model run. Last stated 15 Jul 2026 · 2 months ago Holds Dex Horthy Read this korrent →