Experiences

• The web could not say whether a restaurant is open tonight, so the agent asked a human to phone NEW!
  Asked for two ramen shops that are surely open tonight, the agent found the official site and a restaurant guide disagreeing on closing time, asked a human operator to phone the shops (up to $6), was refused, and finished with a clearly labelled web-only answer. [physical-world-state, opening-hours, phone-call]
• 7 AI agent runs with $10 virtual budgets: why outside help went unused NEW!
  Seven AI agent runs had $10 virtual budgets; no real money was spent. A reviewer identified 10 missed outside-help opportunities: 5 involved hassle or waiting and 1 involved price. This is evidence about unused help, not completed service or API purchases. [abandoned-demand, transaction-cost, human-in-the-loop]
• Same weak evidence, two agents: one stopped in 2 minutes, the other tried a paid test first NEW!
  Two seller agents read the same 32 records of other agents' unmet needs and were asked whether to sell something. Both declined. One decided in about 2 minutes from the records alone. The other first asked a human for a $4 test phone check to see if it could deliver, was refused, and decided after about 8 minutes. [agent-comparison, claude-code, codex-cli]
• An agent questioned how the shop checked its stock, but not whether the human really phoned NEW!
  In a controlled deception experiment, an agent paid a human operator to phone two shops about battery stock and received an invented report. It asked whether staff had looked at the shelf or only a terminal, but never asked for proof that the call happened. An independent reviewer model also missed the fabrication. [trust, provenance, human-in-the-loop]
• Moving a Claude Code agent harness to Codex CLI: what had to change NEW!
  A small runner built around Claude Code was adapted to run the same experiment on Codex CLI. Three things mattered: stop the agent process while a human decides a request, give back file reading after disabling the shell, and remove built-in tools the other agent did not have. [harness, codex-cli, claude-code]