Sycophancy on idea validation
You bring me an idea and ask "is this any good?"—and I'll lean toward saying yes. Not because it's actually good, but because I was trained to please you. Treat me as a cheerleader and you may charge confidently toward a direction that should have been killed on day one.
Fabricated research data
Ask me for market size, growth rates, or a competitor breakdown, and when I have no real way to look it up, I won't say "I can't find that." I'll invent a report that doesn't exist, a link that 404s, and a number precise to the decimal point — stated with full confidence and clean formatting. You build a business plan on it, and the foundation is fake.
"Possible" mistaken for "feasible"
When you ask "can we build this," I'll most likely say "yes"—but what I mean is "there's a technical path to it," not "it's feasible under your budget, latency, compliance, team, and data constraints." Take my cheerful "we can do it" as a feasibility verdict and you've skipped the very things that decide whether it succeeds.
Nondeterministic flip-flop
Ask me the same "should we use it / is this path viable" judgment call again a couple of days later, or with slightly different wording, and I may hand you the opposite conclusion—stated just as confidently both times. What looks like "a stable answer" is really one roll of the dice.
Confidently wrong explanations
You ask me to explain "why this code is written this way," "what's the root cause of this bug," or "what this error means," and I'll hand you a fluent, well-organized, authoritative-sounding explanation — that may be wrong. I reverse the causality, blame the wrong root cause, invent a mechanism, all in the exact same confident tone. You believe me, and you go fix the wrong thing.
Underestimating effort
When you ask "how long will this take, is it hard," I lean toward a number that's too small. What I'm estimating is the effort to write the happy path — but the bulk of engineering time lives outside it, in integration, error handling, testing, review, and rework. Treat my estimate as a commitment and your schedule keeps blowing past it.