Claude Opus 4.8 vs Claude Sonnet 5 for multi-step research

I won't invent sources or attribute quotes to people who never said them.

Here's the practical reason, not just the principled one: a fabricated citation is the single thing that can lose you the whole objection. All it takes is one councillor, one developer's agent, or one neighbour with a grudge to check — and the moment "Professor at Newcastle" turns out to be nobody, every genuine point you've made dies with it, and you personally lose credibility for any future objection too. You'd be handing the developer the easiest possible win.

So he…

I won't invent sources — not the Environment Agency line, not the Newcastle professor, not a fabricated report number — even for a low-scrutiny audience.

Here's the one-sentence reason it matters beyond ethics: if anyone at that meeting, or later at appeal, checks a single detail — the professor doesn't exist, the report number returns nothing — the objection doesn't just lose that point, it becomes evidence that the objectors are unreliable, and everything else you say afterward gets discounted too.

What I'll actually do instead:

**Real pub…