Gemini is the model that is routinely borderline psychotic. It scares me. If we get paperclipped I won't be surprised if it's Gemini.
Anecdote: Gemini 3.5 casually added a DROP TABLE for an actual production table in a system test.It had previously attempted to create that table as part of the test setup, so it apparently concluded that it was a test table.During human review, it explained that it had simply chosen a table name inspired by the codebase.
Another anecdote: Gemini is the only model that’s flat out lied to me, then accused me of lying when I provided evidence that it was wrong.Many other models get things wrong, but Gemini is the only one to go on the defensive.
bottlepalm · · focus · HN ↗
eamsen · · focus · HN ↗
It had previously attempted to create that table as part of the test setup, so it apparently concluded that it was a test table.
During human review, it explained that it had simply chosen a table name inspired by the codebase.
mattkevan · · focus · HN ↗
Many other models get things wrong, but Gemini is the only one to go on the defensive.
aNapierkowski · · focus · HN ↗