“Our working hypothesis is that security will become a fundamental bottleneck to the construction and deployment of superintelligent systems.”In their own words: wittlab.ai
Associate professor at the University of Oxford leading Witt Lab, which studies multi-agent security, including collusion and steganography among language-model agents; incoming associate professor at UCL.
Show detailsHide details
Received $807k from 3 funders
’25
’26
Checked 25 Oct 2026
Money flows
Where their 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
- AI2050$400k
- Coefficient Giving$352k
- Foresight Institute: Funding$55k
All grants
3 grants totalling $807k, newest first.
2026 1 grant · $55k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Mar 2026 | Foresight Institute: Funding | ~$55k | Listed as previously funded on the AI for Science & Safety Nodes page. Affiliation: University of Oxford. Project details and grant date not published; first listed by Mar 2026. — AI for Science & Safety Nodes — listed a source |
2025 2 grants · $752k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 5 Nov 2025 | AI2050 | ~$400k | AI2050 (Early Career Fellow, 2025 cohort): AI2050 Early Career Fellow, 2025 cohort; University of Oxford. Per-fellow amount undisclosed. — AI2050 (Early Career Fellow, 2025 cohort) source |
| Sep 2025 | Coefficient Giving | $352k | Mitigating Collusion in LLMs for Multi-Agent Security (Christian Schroeder de Witt) source |