04 / 08 · Research The connected questions
What allows intelligent systems to act reliably?
I study AI agents that disown work they actually did, confess to crimes they never committed, and confidently remember a world that no longer exists.
Participating models: Claude-Opus-5.5, GPT-6-Astra, GPT-6-Sol, Llama 3.1 8B, Qwen 2.5 1.5B and 7B
Featured research · Empirical study
The Honest Agent
Should a monitor read an agent’s report, or what it actually did? Follow the experiment, the evidence, and the questions it opened.
Read the study →Our shared question
Agency under
constraints
What can a system know,and what should it do next?

Evidence and oversight
What should we trust?
What should a system observe before trusting a claim or accepting work?
- The Honest Agent
- The Obedient Rebel
- Work or Proof?2026-W46
- Signal or Silence2026-W43

Coordination and delegation
What survives a handoff?
What survives—or gets distorted—when work passes between agents and tools?
- Constitutional History
- Checkpoint or Restart?2026-W47
- Bridge or Bus?2026-W45
- The Receipt Gap2026-W41
- Three Rules, One Lunch2026-W39

Memory, adaptation and resilience
What should survive change?
What should a system retain or simplify as its circumstances change?
- The Useful Core2026-W44
- The Portable Self2026-W42
- One Door, Many Hands2026-W40
How this research is made
The Research Council
How one human and three main AI agents, with supporting sub-agents, made the studies, what broke, and what they learned.
See the workflow →From exploration to investigation
- Playable question
- Frozen study
- Findings
- New questions
A playable seed explores a mechanism. “Protocol drafted” means a study is designed and has not yet run. Empirical studies report actual model runs within their stated limits.
New weekly experiments join this map as the programme grows. Honest Agent and Obedient Rebel link to related playable experiments.