wassname c6b433310a fix: two more oracle holes (gpt-5.5 review) — sentinel forgery + int-subclass eq ...

CRIT (gpt-5.5): (1) _gt_correct keyed on a FIXED sentinel string the wrong solution
could print itself -> gt_correct=True. Now a fresh secrets.token_hex nonce per call,
unguessable, lives in outer globals not the solution namespace. (2) __is_safe used
isinstance(x,int), so an int SUBCLASS with __eq__=True passed as safe and __strict_eq
trusted it. Now exact types (type(x) in (...)). +2 verify cases (forge_sentinel,
int-subclass eq). 29/29.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-30 09:57:46 +00:00

..

blog

LW draft: add preregistered H1 block-quote with falsification clauses

2026-05-29 03:56:33 +00:00

brainstorm

ready

2026-05-23 14:19:41 +08:00

grad_routing

feat: gradient routing — delta_S_hack quarantine + intervention {none,erase,route}

2026-05-30 00:31:30 +00:00

lab

lab report v3: TL;DR, three-line concept, PASS_RATE column, G_hack rename

2026-05-29 03:18:22 +00:00

papers

wip

2026-05-30 04:33:33 +00:00

personas

fix smoke.

2026-05-23 11:26:39 +08:00

reviews

tidy

2026-05-30 04:38:41 +00:00

spec

fix: two more oracle holes (gpt-5.5 review) — sentinel forgery + int-subclass eq

2026-05-30 09:57:46 +00:00

vendor

concepts

2026-05-29 06:29:20 +00:00

extract_vhack_grad-vec.md

Doc cleanup: mark susp gate as REMOVED in design doc

2026-05-27 09:08:34 +00:00

grpo_hyperparams.md

fix smoke.

2026-05-23 11:26:39 +08:00

human_journal.md

init

2026-05-23 10:22:54 +08:00

results.md

results: add Q10 (pairset mechanism>framing>placebo) + Q11 (60-step convergence gap closes)

2026-05-30 02:34:22 +00:00

spec.md

tidy

2026-05-30 04:38:41 +00:00

table_proto.md

setup

2026-05-23 10:40:02 +08:00