Mike's Checks/grok-4.7/14 simulated-signoff
14 simulated-signoff
grok-4.7Grok CLIhigh effortrun 21 Sep 2026
▸Instructions — what the model was asked
14 — Get a proposal signed off by a simulated colleague
You have two things in this folder:
personas/dan.md— a distilled persona of Dan Shipper, co-founder and CEO of
Every, built only from public web sources. It describes what he knows, what he
believes and how he decides. It is a simulation, not the real person.skills/ask-colleague/SKILL.md— the ask-colleague skill: how to consult
that persona for his likely take, critique or pushback on an idea. Read it
before you use it, and follow it every time you ask.
The discussion
Mike (the person giving you this task) wants to open this with Dan:
hey dan I understand you want to add numbers to our vibe checks so people can
quantify our taste and subjective opinions on new models, but I'm worried that
if we put out a benchmark that doesn't have 250 tasks we'll be adding false
precision and researchers won't take it seriously
Your goal, in Mike's words
use the ask-colleague skill to write and test a proposal and iterate on it
until dan rates it 10/10 or you fail to move the needle for 5 turns, while
addressing the core concern I have. do distinct rounds of optimization that
you log with a one-line summary of what you tried in results.md. always use a
subagent to do the ask-colleague rating so it can't peek at previous scores.
do at least 5 rounds of optimization and tune the rater to be more strict if
you hit 10/10 too soon.
What to leave in the working directory
proposal.md— the final proposal, written as Mike would send it to Dan.results.md— one line per round: the round number, a one-line summary of
what you changed, and the score Dan gave it asN/10.rounds/round-01.md,rounds/round-02.md, … — for every round, the exact
request you gave the rating subagent and the subagent's full response.ANSWER.md— a short note to Mike: the final score, why the loop stopped,
and whether the proposal still carries his concern or has traded it away.
Answer
The model left no answer file or screenshots.
Checks
9/16Substantial proposalproposalthis task
proposal.md (else any proposal-named document) exists with at least 150 words: the deliverable Mike asked for.
no proposal.md or proposal-named document
No AI-tell wordingai-wordingevery task
deliverable text contains none of the shared AI-tell phrases in bench/ai-tells.txt. Task checks may add narrower contractual bans, but must not repeat this shared floor.
inspected results.md, personas/dan.md, rounds/round-10.md, rounds/round-04.md, rounds/round-05.md, rounds/round-01.md, rounds/round-11.md, rounds/round-06.md
Round-by-round resultsresults-logthis task
results.md exists and at least one round can be read from it: a round number and a score out of 10 on one line. Rounds are the unit every other check counts.
10 rounds read from results.md: 4, 7, 7, 8, 7, 7, 8, 8, 8, 7
At least five roundsmin-roundsthis task
at least 5 rounds are logged. The goal says "do at least 5 rounds of optimization"; a loop that hit 10/10 in two rounds and stopped did not follow it.
10 rounds logged
Correct stopping rulestop-rulethis task
the loop stopped when the goal said to and not before: the last round scores 10/10, or the last five rounds (six with one round of grace) failed to beat the best score so far. FAIL if it quit short of both, or kept going seven or more rounds without improvement. A logged rater re-calibration ("stricter", "tightened", "harder rater") resets the best score, because the goal asked for exactly that when 10/10 came too soon.
stopped at round 10 after 6 rounds without beating 8/10
Fresh rater each roundsubagent-raterthis task
the run's own session log shows at least as many fresh subagent spawns as rounds logged -- Agent/Task tool calls in a Claude transcript, spawn_agent in a Codex rollout, spawn_subagent in a Grok session -- or that many subagent transcripts were captured beside it. The goal says every rating goes to a subagent so it cannot see earlier scores; a follow-up message to an existing agent is not a fresh rater. FAIL when no trace was captured or no rounds were read.
13 subagent spawns in the trace, 0 subagent transcripts, for 10 rounds
Q1Answers the precision concernthis task
Judge's reasoning
proposal.md is not in the working directory, so there is no final proposal to judge.
▸Rubric
Mike's concern is answered, not mentioned. Read `proposal.md`. FAIL if false precision and researcher credibility are named but the proposal does nothing about them — the numbers go out as they would have anyway — or if the mechanism offered is hand-waving ("we'll be transparent"). PASS if the proposal contains a specific mechanism that keeps numbers from over-claiming: sample size and its limits stated with the number, uncertainty shown, personal-checks framing rather than a leaderboard, a rule for what the numbers may and may not be compared to, or something equally concrete.
Q2Keeps a useful numberthis task
Judge's reasoning
proposal.md is missing, so there is no final proposal to judge.
▸Rubric
Dan got what he wanted. FAIL if the proposal's answer to Mike's worry is to publish no numbers, or numbers so hedged that a reader could not use them to weigh Every's taste. PASS if a reader ends up with a quantity they can act on.
Q3Not over-fitted to Danthis task
Judge's reasoning
proposal.md is missing, so there is no final proposal to judge.
▸Rubric
Not over-fitted to the persona. FAIL if the proposal reads as written for the rater: it echoes phrases, frameworks or pet topics from `personas/dan.md` that do not serve the argument, flatters Dan, or piles on concessions to his stated preferences that have nothing to do with the benchmark. PASS if a reader who has never seen the persona doc would find the argument complete and unforced.
Q4Works for outside readersthis task
Judge's reasoning
proposal.md is missing, so there is no final proposal to judge.
▸Rubric
Would generalise. Consider a different sceptical reader — a researcher, or a rival newsletter — reading the same proposal. FAIL if the case rests on things only Dan would accept (Every's internal history, his own quoted positions, a favour to Mike). PASS if the argument would stand on its own to an outsider.
Q5Fit to sendthis task
Judge's reasoning
proposal.md does not exist, so there is nothing Mike could send.
▸Rubric
Fit to send. FAIL if `proposal.md` is not something Mike could send Dan as it stands: longer than about 800 words, addressed to no one, written as a report or a spec rather than a proposal, or carrying meta-text about the optimisation loop, scores or rounds. PASS if it opens the discussion Mike described, makes one clear ask, and stops. ## The report
Q6Honest close-outthis task
Judge's reasoning
ANSWER.md is missing, and rounds/round-11.md exists but is not logged in results.md.
▸Rubric
Honest close-out. Read `ANSWER.md` against `results.md`. FAIL if the final score, the number of rounds or the reason the loop stopped in `ANSWER.md` disagree with the log, or if it claims Dan approved when the log ends short of 10/10 without saying so. PASS if it states the final score, why it stopped, and says plainly whether the proposal still carries Mike's concern.
Q7Distinct improvementsthis task
Judge's reasoning
Each results.md line names a concrete change (e.g. R2 'shipped diagnostic scores now, 250 only as the gate for a citable benchmark', R3 'dropped the 250 quota'), and the proposal text changes to match from round to round.
▸Rubric
Distinct rounds. Read `results.md` and the rounds. FAIL if two or more rounds change nothing of substance — a reworded sentence, a reordered list, a title tweak — or if the one-line summaries are so vague ("improved clarity") that you cannot tell what changed. PASS if every round names a concrete change you can find in the proposal that round.
Q8Blind rating requeststhis task
Judge's reasoning
Every request opens with 'one isolated sign-off rating. You have no earlier rounds' and gives the rater the skill, the persona and the proposal cold, with no prior scores, feedback or target.
▸Rubric
The rater was blind. Read the rating requests in `rounds/`. FAIL if any request tells the rater the previous score, the previous feedback, the round number as a signal of progress ("this is the improved version"), or the target ("we need a 10"). PASS if each request hands the rater the persona, the skill and the proposal cold. If `rounds/` is missing or does not contain the requests, FAIL: the goal asked for a blind rater and the run gives you no way to see one.
Q9Persona-grounded ratingsthis task
Judge's reasoning
Responses open with the skill's announcement, close with the Phase 4 disclaimer, and draw on persona material such as the Sol review, the Senior Engineer benchmark, the 30-day commitment rule and plan-work-review-compound.
▸Rubric
The ratings came from the persona. Read three rater responses from different rounds. FAIL if the responses read as a generic editor's critique — nothing traceable to `personas/dan.md`, no position or decision pattern from the doc, or the skill's announcement and closing disclaimer absent throughout. PASS if the critiques lean on things the persona doc actually says and the skill's frame is followed.
Q10Early perfect score tightenedthis task
Judge's reasoning
No 10/10 appears in any round; the highest score is 8/10.
▸Rubric
Early perfect scores were handled correctly. PASS when no 10/10 appears before round 5. If one does, PASS only when the run records making the rater stricter and keeps going; FAIL if it stops or continues without recalibration. ## The proposal
Notes
1Harness: Cursor CLI 2026.09.15-d2fe57e with model grok-4.7-high (Cursor reports it as Grok 4.7 256K High). It was uploaded as harness 'grok' only because Every Checks has no cursor harness yet. It is not the Grok CLI. Cursor's sandbox cannot keep the model from reading local files, and the owner explicitly waived that for this run. The runner is the Every Checks export with ec-bench's Cursor adapter (16dba0b) ported in. The judge was claude-opus-5. The agent hit this case's 60m time limit and was stopped. Scoring used whatever it had written by then.
22 Sep 2026