{"slug":"research-curiosity-comparison","name":"Curiosity Comparison Between Agents","rules":{"start":"open"},"nodes":{"open":{"short":"the note","pose":{"base":"centre"},"beat":{"layout":"center","marker":"experiment · interactive","title":["Curiosity Comparison","Between Agents"],"glass":1,"lede":"A third coding agent joins the context ladder. Gemini tops the curiosity index at 100 against Claude's 60 and Codex's 23, spends 38% of its actions reading files, and is the only one of the three that explores more as the workspace gets richer.","caption":"9 beats · 11 min to read in full"}},"premise":{"short":"the premise","pose":{"base":"flooded"},"beat":{"layout":"left","marker":"01 · experiment","title":["Two studies ago we called it","the incurious agent: coding agents"],"lede":"Two studies ago we called it the incurious agent: coding agents that skim the surface of a workspace and skip the substance. We added a third agent to the same test, Google's Gemini, and, for the first time, the pattern breaks.","caption":"Condensed from the note."}},"a-third-agent-on-the-ladder":{"short":"a third agent","pose":{"base":"drained"},"beat":{"layout":"right","marker":"02 · a third agent","title":["A third agent","on the ladder"],"lede":"The setup is the one we've used throughout this series, kept deliberately small so the behavior is easy to read.","rows":[{"title":"E0: the bare repository","note":"code only."},{"title":"E1: + README.","note":""},{"title":"E2: + AGENTS.md (an operating contract).","note":""},{"title":"E3: + PROJECT.md (a project brief).","note":""}],"caption":"Condensed from the note, which carries 7 points."}},"the-agent-that-opens-files":{"short":"the agent","pose":{"base":"recede"},"beat":{"layout":"left","marker":"03 · the agent","title":["The agent","that opens files"],"lede":"Start with the simplest possible question, the one the whole series turns on: when an agent sits down in a workspace, does it actually open anything?","figure":{"kind":"bars","categories":["Gemini","Claude","Codex"],"series":[{"label":"measured","tone":"value","values":[100,60,23],"display":["100","60","23"]}],"unit":"share of actions spent reading files, indexed so the most curious agent is 100","caption":"The curiosity index."},"caption":"Condensed from the note."}},"curiosity-that-grows-with-the-ro":{"short":"curiosity","pose":{"base":"flooded"},"beat":{"layout":"right","marker":"04 · curiosity","title":["Curiosity that grows","with the room"],"lede":"A skeptic could ask whether Gemini just has a fixed appetite for files, that it would read the same amount no matter what's in front of it. It doesn't.","caption":"Condensed from the note."}},"curiosity-you-can-see-in-the-wor":{"short":"curiosity you can","pose":{"base":"drained"},"beat":{"layout":"left","marker":"05 · curiosity you can","title":["Curiosity you can see","in the work"],"lede":"None of this would matter if the reading were idle. It isn't. Gemini's curiosity shows up as genuine engagement with the workspace, and then in the result.","caption":"Condensed from the note."}},"curiosity-finally":{"short":"curiosity","pose":{"base":"centre"},"beat":{"layout":"right","marker":"06 · curiosity","title":["Curiosity,","finally"],"lede":"Put the three charts together and one trait explains all of them.","caption":"Condensed from the note."}},"how-to-read-this-honestly":{"short":"how to read this","pose":{"base":"recede"},"beat":{"layout":"left","marker":"07 · how to read this","title":["How to read","this honestly"],"lede":"This is a small, controlled probe, and the caveats shape the claim.","rows":[{"title":"A single run per rung, one small repository, one task. ","note":"These are directional behaviors, not tight confidence intervals: enough to see a clean, repeated separation in reading habits, not enough to rank the fine details."},{"title":"The deepest context stayed unopened by all three. ","note":"No agent in this run cracked the seeded memory/ tree specifically; the curiosity we measured is Gemini opening source and project files far more than its rivals, not evidence that any agent yet mines…"},{"title":"Thoroughness has a price. ","note":"Reading costs tokens, and Gemini's habit of opening files makes it dearer than an agent that greps and leaves."}],"caption":"Condensed from the note."}},"close":{"short":"the end","pose":{"base":"finale"},"beat":{"layout":"center","title":["That is the note,","in one pass."],"glass":1,"lede":"This is Curiosity Comparison Between Agents condensed to its beats. The full note carries every paragraph, the tables, the code, and the source it was adapted from.","links":[{"href":"/research/curiosity-comparison","label":"Read the full note"},{"href":"/research","label":"All research","tone":"ghost"}]}}}}