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 subject Same subject Same subject Same subject Same subject Same subject Same subject Same 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 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 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 model rather than the real system is worth doing even though the real 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 is not prompt engineering but giving a model a way to verify its 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 rigorous than traditional engineering; its record-keeping and automated 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 codebase quality, not on shipping the features users want; we read all 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 of formal methods because they were 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 verification is not proving the code correct but working out what the 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, the standard example of software that 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 slow simulators change what science is possible, by turning a six-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 wording a cloud: claims about one subject, named for it bar: how recently it was last stated — full and dark this week, a faint sliver at five years a face: someone on record holding the claim — tap it for who they are