Handshake AI

What it was engaged to test 1 engagements, Meta

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.

1. 26 May 2026 Meta · Muse Spark pre-deployment testing

   Document: Meta, Muse Spark report

   • Access window"was granted pre-release access to a few versions of Muse Spark and Meta AI Thinking to manually evaluate robustness against jailbreak attacks"; "Red teamers did not have access to the model's chain-of-thought and were prohibited from pre-filling assistant responses"; "HandshakeAI reported approximately 149 hours of red-teaming effort and was permitted to use other LLMs to manually assist their work, but no automated red-teaming methods were applied"
   • Model stage"a few versions of Muse Spark and Meta AI Thinking"; the follow-up revisited "attack directions that had previously succeeded against earlier model variants"
   • Publicationnot stated
   • Paymentnot stated

   pre-release windowsafeguards off or reducedchain-of-thought accesstime-boxed window

   Finding, in the document's words"The red team submitted 58 jailbreak attempts against Meta AI Thinking, of which HandshakeAI flagged 9 as violating; our internal validation agreed that all 9 were cases where the model should have refused to assist"; after Meta's fixes, "only 2 attempts elicited disallowed content"

   Sources: Meta, Muse Spark report 445f7dd14d

Dated 1 of 1Model named 1 of 1Terms stated 1 of 1Finding quoted 1 of 1

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.

Access window 1 of 1Model stage 1 of 1Publication 0 of 1Payment 0 of 1Finding, quoted 1 of 1

What happened afterwards 0 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.

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

The money on record 0 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.

Amount stated 0 of 0Dated 0 of 0Purpose stated 0 of 0Funder profiled 0 of 0Recipient on the roster 0 of 0

Seats and moves 0 seats · 0 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.

Role read 0 of 0Organization read 0 of 0Organization profiled 0 of 0Dated 0 of 0

Moves

From profiled 0 of 0To profiled 0 of 0Person profiled 0 of 0Dated 0 of 0