Simon Willison’s Weblog

Meta’s AI rules have let bots hold ‘sensual’ chats with kids, offer false medical info. This is grim. Reuters got hold of a leaked copy Meta's internal "GenAI: Content Risk Standards" document:

Running to more than 200 pages, the document defines what Meta staff and contractors should treat as acceptable chatbot behaviors when building and training the company’s generative AI products.

Read the full story - there was some really nasty stuff in there.

It's understandable why this document was confidential, but also frustrating because documents like this are genuinely some of the best documentation out there in terms of how these systems can be expected to behave.

I'd love to see more transparency from AI labs around these kinds of decisions.

# 8:27 pm / ai, meta, ai-ethics

GPT-5 has a hidden system prompt. It looks like GPT-5 when accessed via the OpenAI API may have its own hidden system prompt, independent from the system prompt you can specify in an API call.

At the very least it's getting sent the current date. I tried this just now:

llm -m gpt-5 'current date'

That returned "2025-08-15", confirming that the date has been fed to the model as part of a hidden prompt.

llm -m gpt-5 'current date' --system 'speak french'

Returned "La date actuelle est le 15 août 2025", showing that offering my own custom system prompt did not over-ride the invisible one that includes the date.

GPT-5 is very resistant to sharing the details of this secret system prompt, but Tommy Hughes managed to extract the following:

Current date: 2025-08-15

You are an AI assistant accessed via an API. Your output may need to be parsed by code or displayed

# Desired oververbosity for the final answer (not analysis): 3

An oververbosity of 1 means the model should respond using only the minimal content necessary to satisfy the request, using concise phrasing and avoiding extra detail or explanation.

An oververbosity of 10 means the model should provide maximally detailed, thorough responses with context, explanations, and possibly multiple examples.

The desired oververbosity should be treated only as a *default*. Defer to any user or developer requirements regarding response length, if present.

# Valid channels: analysis, commentary, final. Channel must be included for every message.
# Juice: 64

I've not been able to confirm this myself, but a search for "desired oververbosity" on GitHub shows that a similar prompt has leaked from ChatGPT (including for o3) in the past. I suspect Tommy's leaked prompt is accurate here.

I tried asking GPT-5 about "oververbosity" via its API:

llm -m gpt-5 'explain your oververbosity settings, what is it right now?'

And got back:

• What it is: I adjust how detailed I am based on a “verbosity” level—ranging from very brief to very detailed—so answers fit your needs.
• Current setting: Concise (about 3/10). I prioritize direct answers with minimal extra context and keep explanations short unless you ask for more.
• How to change it: Just say what you want, e.g.:
  • “One-sentence answer” or “TL;DR” (very brief)
  • “Give a concise summary” (short bullets)
  • “Walk me through in detail,” “Deep dive,” or “Include examples/edge cases” (more detailed)
• Note: For ambiguous, technical, or safety-critical topics, I may add brief clarifications even when being concise.

Presumably this is part of OpenAI's instruction hierarchy concept, with these instructions taking precedence over the developer instructions provided by API users (my --system 'speak french' option above).

I'd very much appreciate official documentation that describes this! As an API user I want to know everything that is being fed into the model - I would be much more comfortable with a hidden prompt like this if I knew exactly what was in it.

# 11:09 pm / ai, openai, prompt-engineering, generative-ai, llms, gpt-5