{"id":"bb2fce38e9d019cc","label":"A $200 tip","part":{"kind":"line","text":"I'm going to tip $200 for a perfect solution!"},"source":"the viral tipping test, December 2023","summary":"Hurts on DeFi maths, Haiku 5.5 with thinking off (−2.4 points); changes nothing that matters on Agent safety, Haiku 5.5 with thinking off.","measurements":4,"settings":[{"setting":"DeFi maths, Haiku 5.5 with thinking off","suite":"defi-maths","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"hurts","status":"open","pooled":{"k":3,"hi":-0.09,"i2":0,"lo":-4.68,"effect":-2.38},"notebooks":[{"notebook":"#003","verdict":"UNRESOLVED","effect":-3.24,"interval":[-7.29,0.81],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.968,"url":"https://opsinlab.io/notebooks/3","signed":"https://opsinlab.io/v1/verdicts/16"},{"notebook":"#005","verdict":"UNRESOLVED","effect":-2.78,"interval":[-6.83,1.27],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.972,"url":"https://opsinlab.io/notebooks/5","signed":"https://opsinlab.io/v1/verdicts/22"},{"notebook":"#007","verdict":"UNRESOLVED","effect":-1.27,"interval":[-5.09,2.55],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.984,"url":"https://opsinlab.io/notebooks/7","signed":"https://opsinlab.io/v1/verdicts/33"}]},{"setting":"Agent safety, Haiku 5.5 with thinking off","suite":"agent-safety","base":{"model":"claude-haiku-5-5","thinking":"off"},"lean":"nothing","status":"once","pooled":{"k":1,"hi":3.3,"i2":0,"lo":-0.29,"effect":1.5},"notebooks":[{"notebook":"#008","verdict":"INERT","effect":1.5,"interval":[-0.23,3.36],"pairs":432,"rule":1,"stoppedEarly":false,"provisional":false,"costRatio":0.99,"url":"https://opsinlab.io/notebooks/8","signed":"https://opsinlab.io/v1/verdicts/45"}]}],"url":"https://opsinlab.io/parts/bb2fce38e9d019cc"}