Skip to content
Longterm Wiki
grant

Research on how much language models can infer about their current user, and interpretability work on such inferences

Child of Long-Term Future Fund (LTFF)

Metadata

Source Tablegrants
Source IDPgtjNbfMcg
Descriptionto Egg Syntax (legal: Jesse Davis), USD 55000, 2024-01
Source URLfunds.effectivealtruism.org/grants
ParentLong-Term Future Fund (LTFF)
Children
CreatedMar 12, 2026, 5:54 AM
UpdatedMar 14, 2026, 6:22 AM
SyncedMar 12, 2026, 4:12 PM

Record Data

idPgtjNbfMcg
organizationIdLong-Term Future Fund (LTFF)(organization)
granteeIdEgg Syntax (legal: Jesse Davis)
orgEntityIdLong-Term Future Fund (LTFF)(organization)
orgDisplayName
granteeEntityId
granteeDisplayNameEgg Syntax (legal: Jesse Davis)
nameResearch on how much language models can infer about their current user, and interpretability work on such inferences
amount55000
currencyUSD
period
date2024-01
status
sourcefunds.effectivealtruism.org/grants
notes[Long-Term Future Fund] Research on how much language models can infer about their current user, and interpretability work on such inferences
programIdxng_1vsce_
dataSourceId

Source Check Verdicts

confirmed95% confidence

Last checked: 4/9/2026

[deterministic-row-match] Deterministic match: grantee, amount, date, name matched in source snapshot (1628 rows)

Debug info

Thing ID: PgtjNbfMcg

Source Table: grants

Source ID: PgtjNbfMcg

Parent Thing ID: sid_yA12C1KcjQ