“AI agents drift from human intent over long-horizon tasks. We infer their plans with uncertainty-aware representations to keep humans in the loop.”In its own words: recursive-safeguarding.org
A UK research company studying how AI agents drift from human intent on long tasks, inferring their plans with uncertainty-aware representations to keep humans in the loop.
Show detailsHide details
Received $725k from 2 funders
’25
’26
Led by Younesse Kaddar (Director (sole company officer)), Rob Cornish (team member), Sam Staton (team member (Professor)Checked 26 Oct 2026
Money flows
Where its money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.
Funded by
All grants
2 grants totalling $725k, newest first.
2026 1 grant · $590k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 19 Feb 2026 | The Alignment Project | ~$590k | Alignment Project round 1 (lead: Kaddar, Younesse): Bayesian Scientist AI for LLM Agent Alignment: GFlowNet-sampled plan abstractions and white-box monitors to mitigate drift and deception. Amount undisclosed; awards £50k–£1M from a £27m pool across 60 announced projects. source |
2025 1 grant · $136k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 18 Jul 2025 | Advanced Research + Invention Agency | $136k | Safeguarded AI TA2 Phase 1 (grant, 3 months); £106,750 incl. VAT; technical area inferred source |