evilrobots.lol / tech / evaluator record

ARC

ALIGNMENT RESEARCH CENTER (ARC). What it was engaged to test, on what terms, what it found in the document's own words, and what happened afterwards. Every line is a record; every record links to the document it was read from.

▣ THE RECORD nonprofit The METR / Redwood / ARC core STORE 2026-10-18
  • Foundednot stated
  • HQnot stated
  • Registry idEIN 86-3605182
  • Testsalignment-theory nonprofit; executive director and president Paul Christiano; board Christiano, Buck Shlegeris, Ben Hoskin; its evaluations team became METR
  • Money, as the roster puts itnot stated
  • Filesdossier · observatory, sliced to it · graph
Labs tested
no lab document names it
Models
no model named
Span of engagements
none dated
Terms and findings
0 of 0 documents state a term · 0 quote a finding
Money in, US dollars, stated single-recipient rows
$7,138,000 5 in · 0 outfrom Coefficient Giving · Survival and Flourishing Fund
Seats, by side
evaluator 4 between 1 5 people: Beth Barnes, Buck Shlegeris, Holden Karnofsky, Kyle Scott, Paul Christiano
Afterwards
staff move 2

Each count is the number of store records that name this evaluator. An engagement is one lab document naming it for one model; an outcome is an event on the record afterwards; the money, seats and moves are the observatory's rows filtered to it. A cell that cannot be filled says not stated, and each table ends with how many of its rows state each field.

▣ SLICE 17 / 17 records
Lab
Outcome
Funder
Person
year, month or day

Filters combine: any of the values ticked within a dimension, all of the dimensions at once. A table that has no column for a dimension you have set says so instead of showing rows that cannot match. The address bar carries the slice.

What it was engaged to test 0 engagements

In date order, each from the lab document that names the evaluator. Under each: the four terms that document states (access, model stage, publication, payment) and the finding in its words. A term the document is silent on reads not stated; the tags beside the terms are read off their words and are what the console filters on.

No lab document on record names this evaluator for a model.

Dated 0 of 0Model named 0 of 0Terms stated 0 of 0Finding quoted 0 of 0

The terms, as the documents state them

The same engagements as a grid, one row per document and model, so the silences line up: a document that gives an access window but no payment term, or a finding but no publication term, reads that way here.

DocumentModelAccess windowModel stagePublicationPaymentFindingRecord
no engagement on record

Access window 0 of 0Model stage 0 of 0Publication 0 of 0Payment 0 of 0Finding, quoted 0 of 0

What happened afterwards 2 on record

Events a party published after an engagement: an incident on a model this evaluator's engagement covered, a correction or added disclosure, a later finding that cut against an earlier one, a lab's statement that it acted or did not act on the finding, or a move from this evaluator to a lab it graded. A row the source attaches to this evaluator by name is marked named; one that reaches it through the model it tested is marked via the model. The kind is what the record states, not why.

KindDeveloperModelWhat the record statesWhenSourceId
staff movenamed · reportedAnthropicno model namedHolden Karnofsky: ARC board (to Apr 2023) -> Anthropic (technical staff, Jan 2025, reported)Jan 2025EA Forum; Fortunefca6706722
staff movenamedOpenAIno model namedPaul Christiano: ARC; US AI Safety Institute (Apr 2024); CAISI senior technical adviser; back to ARC as executive director (Aug 2026) -> OpenAI Foundation board (9 Sep 2026)Engagements: 63740c1c85, aef969d6879 Sep 2026NIST; OpenAI Foundation; ARC47b741082c

Dated 2 of 2Model named 0 of 2Tied to an engagement 1 of 2Evaluator named by the record 2 of 2

The money on record 5 rows · $7,138,000 in, stated single-recipient rows

Rows of the observatory's money table that name this evaluator as recipient (in) or as funder (out), each as the record states it: a grant table line, a contract notice, a Form 990 schedule or the party's own disclosure. A figure quoted in prose is marked and never summed.

DirectionFunderRecipientAmount, as recordedWhenRecordSourceId
inCoefficient GivingARC$265,000$265,000 (Mar 2022)Mar 2022grant databaseCoefficient Giving24020f82d0
inCoefficient GivingARC$1,250,000$1,250,000 over two years (Nov 2022)over two yearsNov 2022grant databaseCoefficient Givinga151c338fc
inSurvival and Flourishing FundARC$2,179,000$2,179,000 (2022-H2)2022-H2grant databaseSFF-2022-H2; SFF-2023-H1; SFF-2024d77fe32fcc
inSurvival and Flourishing FundARC$3,247,000$3,247,000 for the Evals Team (2023-H1)for the Evals Team2023-H1grant databaseSFF-2022-H2; SFF-2023-H1; SFF-202488aee8f189
inSurvival and Flourishing FundARC$197,000$197,000 (2024)2024grant databaseSFF-2022-H2; SFF-2023-H1; SFF-2024a40cdb0887

Amount stated 5 of 5Dated 5 of 5Purpose stated 2 of 5Funder profiled 5 of 5Recipient on the roster 5 of 5

Seats and moves 5 seats · 4 moves

Seats read off a team page, a governance page, an appointment notice or a filing that name this organization, and the dated moves into or out of it, from the observatory's own tables.

PersonSideSeat, as the record states itRoleDatesSourceId
Beth Barnesslice evaluatorFounder and CEO, METR (Dec 2023); led ARC Evals from 2022names this evaluator alongside its own organizationFounder and CEODec 2023 – current, as readMETR; METR, 19 Sep 2023; AXRP 34e92f2f3f06
Buck Shlegerisslice evaluatorboard member, Alignment Research Centerboard memberdates not statedARCede863b9d0
Paul Christianoslice evaluatorFounder and executive director, Alignment Research Center, from which METR spun outFounder and executive directordates not statedARC; METR, 19 Sep 20233b139b8428
Holden Karnofskyslice evaluatorBoard, Alignment Research Center, to Apr 2023Boardformer– Apr 2023ProPublica0f3e9faea4
Kyle Scottslice betweenTreasurer, Alignment Research CenterTreasurerdates not statedPalisade; ARCf4ef777b22

Role read 5 of 5Organization read 5 of 5Organization profiled 5 of 5Dated 2 of 5

Moves

PersonFromToWhenSourceId
Beth BarnessliceOpenAI→Alignment Research Center (ARC Evals), then METRSummer 2022; Dec 2023AXRP 34; METR208503bfc8
Paul ChristianosliceOpenAI (2017 to 2021)→ARC; US AI Safety Institute (Apr 2024); CAISI senior technical adviser; back to ARC as executive director (Aug 2026); OpenAI Foundation board (9 Sep 2026)2021 to Sep 2026NIST; OpenAI Foundation; ARC30fdcfdee3
Kyle ScottsliceMETR (Operations Manager)→Palisade Research board; ARC Treasurerby 2026Palisade; ARC7a4af92c25
Holden KarnofskysliceOpen Philanthropy (co-CEO, to 29 Apr 2024); ARC board (to Apr 2023)→Anthropic (technical staff, Jan 2025, reported)2024 to 2025EA Forum; Fortune70aff7d6b7

From profiled 4 of 4To profiled 4 of 4Person profiled 4 of 4Dated 4 of 4

Filings