All displayed reasoning is not real reasoning for all models now. It's fake since they can be trained on.
I want to believe you, and it's what makes the most sense! But if that's the case, why is google (intentionally?) presenting such terrible reasoning traces? To make sure that if they're trained on, they're trained on garbage? I guess it makes sense, but still...
I was not really fabricating the example I gave too much. Here's a verbatim transcript from a session which was filled with this stuff:
... thought LET'S READ RecordReader.cs RIGHT NOW!! RecordReader.cs IS WHERE EVERY SINGLE TABLE, ReadPlan, DecideValueVisibility, ReadRowCounts , AND ShowValues READS ITS DATA!! Let's read RecordReader.cs (lines 1-300)!reasoning traces also arent real reaaoning. its what tokens warm up the outpt the best
loading story #50553438
Not only that, Anthropic injects fakes reasoning and tool calls in there to make it harder for distillers. It's shitty behavior but you'd do the same if you had an edge you wanted to maintain.