Skip to content
Longterm Wiki
grant

SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents

Child of Manifund

Metadata

Source Tablegrants
Source IDu1061Zg7Av
Descriptionto Agustín Martinez Suñé, USD 1975, 2025-01-07
Source URLmanifund.org/projects/safeplanbench-evaluating-a-guaranteed-safe-ai-approach-for-llm-based-agents
ParentManifund
Children
CreatedMar 12, 2026, 4:59 PM
UpdatedMar 14, 2026, 6:22 AM
SyncedMar 12, 2026, 4:59 PM

Record Data

idu1061Zg7Av
organizationIdManifund(organization)
granteeIdAgustín Martinez Suñé
orgEntityIdManifund(organization)
orgDisplayName
granteeEntityId
granteeDisplayNameAgustín Martinez Suñé
nameSafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents
amount1975
currencyUSD
period
date2025-01-07
status
sourcemanifund.org/projects/safeplanbench-evaluating-a-guaranteed-safe-ai-approach-for…
notes[Technical AI safety, AI governance] Seeking funding to develop and evaluate a new benchmark for systematically assesing safety of LLM-based agents
programId8jnn54YEbQ
dataSourceId

Source Check Verdicts

confirmed95% confidence

Last checked: 4/11/2026

All key fields are confirmed by the source text. The grant name, amount ($1,975), grantee (Agustín Martinez Suñé), and funder (Manifund) are all explicitly stated on the project page. The date of 2025-01-07 is reasonable given the edit timestamp of November 14, 2025, and the project's active status in early 2025. The source clearly shows this is a Manifund grant to Agustín Martinez Suñé for exactly $1,975.

Debug info

Thing ID: u1061Zg7Av

Source Table: grants

Source ID: u1061Zg7Av

Parent Thing ID: sid_fFVOuFZCRf