GPT-5.6 is killing it when given personas. Here’s a starter pack
OpenAI’s Sol flagship seems to make surprisingly good use of prompted personas. It just so happens that I have examples ready to roll.
Remember those long-ago, early days of prompt engineering, when we were all like “act like a 56-year-old research assistant working for a really strict professor” to desperately get decent output from LLMs?
2024, man, what wild yet innocent times those were.
In the thousand years of AI development since, every LLM has started to sound exactly the same, and there was nothing to be done about it.
Until, maybe, now.
I don’t have direct access to OpenAI’s Sol, GPT-5.6, but I know people who know people who share my obsession with tone and risk in writing, and we ran some tests – and they’re looking really good. Between 5.5 and 5.6 there was a shift (probably in guardrails, this being a mechanism ancient jailbreakers used to get around them) that means GPT will at least try to honour a prescribed persona in writing.
This will not make for writing with impact. Good writing only happens if you care enough to take some risks, and an LLM won’t get you there. However, it might just take us to a place where an LLM can help adjust your tone and language to meet your objectives.
As it happens, I’ve been preaching personas – for human writers – for years. And recently selling them.
This is an excerpt from what I hear is a quite excellent book you should totally buy, called Write Risky. It covers how to assume personas in your writing, but includes a starter pack with descriptions that you can cut-n-paste into an LLM with increasingly good results.
But the author is all like “I write for money”, so this is where the paywall comes down, sorry.
