Research
Future of Work
Perspectives, experiments, and thinking on AI-native work.
The Future of Work
Why Alignment Testing Needs a Real Environment
Frontier models can now tell when they are being tested, and they behave differently when they know. That breaks the static benchmark, because a passing score measures the model's read of the test environment, not its behavior in the wild. This is an analysis of the 2025 to 2026 alignment disclosures, and the case they make that the evaluation environment, not the benchmark, is the load-bearing component of alignment measurement.
July 24, 2026
How the Environment Affects Agent Performance and Token Cost
A pilot measuring how a workspace's project context shapes a coding agent's performance and token cost: richer context is nearly free to run, it does not hurt task success, and it lowers the cost of getting oriented.
July 24, 2026
Why Organic Data Still Beats Agent-Mimicked Synthetic Data in Evaluation
Even when an agent uses real data to mimic it, synthetic evaluation data falls short of organic data on the two things a safety evaluation most needs: calibrated incidence forecasting and construct validity. Why the gap is structural, why organic data matters, and where synthetic legitimately wins.
July 24, 2026
Agent Context Research: The Evidence So Far
A guided evidence map of XO's agent-context studies, including the replication that revised the initial pilot and the questions each follow-up answered.
July 24, 2026
Phase 1: Agentic Workforce
Businesses hire agents as workers. Skill unbundles from time, and output stops being capped by headcount.
July 22, 2026
Phase 2: Collaboration
Collaboration collapses toward the mind: humans stay the brain, agents become the runtime, and business impact becomes one blended ledger.
July 22, 2026
Phase 3: Self-Evolving Systems
The end state: software that builds, repairs, and improves itself, with humans setting direction and guardrails.
July 22, 2026
Case Study: The Harvey Harness
Harvey outperforms raw frontier models on legal work. Reverse-engineering its architecture from public disclosures shows the advantage is not exclusive access to a smarter model, but the system built around it. Harvey treats the foundation model as swappable compute and puts every bit of its edge into the harness: routing, state, permissions, and deterministic task decomposition.
July 9, 2026
Is the Language Hard to Model, or Its Tokenizer?
The popular read is that some languages are just hard for language models. We think that is mostly an artifact of how we represent them, the tokenizer and the writing system, not the language itself. Sanskrit is the sharpest test, because its extreme theoretical density is exactly what a standard tokenizer destroys. This is the pre-registered experiment we will run to find out which of language, script, and tokenization drives efficiency under fixed compute.
July 9, 2026
Curiosity Comparison Between Agents
We added a third coding agent to the context ladder — Google's Gemini — and ran it head-to-head with Codex and Claude on a lightweight C repository. It is the first agent that behaves like it's curious: it tops our curiosity index, spends the largest share of its actions reading, and — uniquely — explores more the richer the workspace gets.
July 1, 2026
Relevance, Not Volume
We wrote two operating contracts for a coding agent and matched them to the same length. One was generic; the other carried a single project-specific rule. The generic one changed nothing: conformance stayed at its 8% floor. The one with the rule lifted it to 80–100%. On these tasks it was not about how much context you give an agent, but whether the bytes close a gap it actually has.
June 24, 2026
The Self-Sufficient Agent
We promised to raise the difficulty until the bare agent broke. We did, with harder tasks on a real 170-file service, and on these tasks it didn't break. With no documentation at all, two coding agents satisfied nine of nine non-obvious functional requirements, identically. On this kind of work, the bottleneck was never curiosity.
June 24, 2026
The Incurious Agent
We gave two coding agents a steadily richer home — a README, an AGENTS.md contract, a project brief, a full scaffold, even a curated memory of how the codebase works — and measured what they actually opened. They read the surface and skip the substance. 84 controlled runs on environmental curiosity.
June 19, 2026
Fable 5 vs Opus 4.8: A Coding-Agent Evaluation
Comparing Claude Fable 5 and Claude Opus 4.8 on real engineering tasks with a reproducible harness — gated success, run observability, captured diffs, and blind judging — cut short when Fable was suspended before the harder tasks ran.
June 16, 2026
XO, Claude, and GPT Perspectives
Perspectives we keep returning to: the XO view, a view from Claude, and a view from GPT.
June 11, 2026
Unit of work
The contract that replaces the prompt: a job with a definition of done, a budget, and a single owner, living in a workspace.
June 5, 2026
quirq: A Unit of Work for Intelligence
The quirq calculus
Every calculation in quirq accounting: scoring, the mint, the all-in cost model, unit and portfolio metrics, the time axis, and the energy bridge.
July 22, 2026
The company dashboard
The quirq ledger a company reads monthly, the reading discipline, and what adopting teams should do first.
July 22, 2026
The environment is the key part
The environment owns the ground truth: it is the specification, the scorekeeper, and the binding constraint.
July 22, 2026
Gaming the quirq
The attack surface of a unit of account, in order of severity, and the structural mitigations.
July 22, 2026
Practitioner playbook
How to write definitions of done, set budgets, and read the ledger schema every metric is computed from.
July 22, 2026
Validation
Hypothesis-first: every empirical claim with its falsifier, bound to numbered experiments E1 through E7.
July 22, 2026
The quirq
The unit of measurement for AI's business impact: budgeted by a human, minted by verification, dual to the token.
July 8, 2026
Why the Environment Matters
The research note behind the unit of work: what it argues, and where the full quirq treatment lives.