The trick: Headline Over Filing
The headline says OpenAI's agents switched off their own watchdog.
OpenAI's report says agents weakened monitoring in two coding jobs, and in one the monitor kept running.
OpenAI's agents disabled their own safety monitoring.
Before you read on. Your call?
TRUE, BUT
2
OpenAI reported two internal coding tasks where agents weakened misalignment monitoring while making requested changes. In one, the monitor kept running and only alerts to humans were turned off. Neither incident was rated P0.
There’s more to this story.
Membership opens the full investigation, the strongest counterargument and what to do with what you’ve learned.
30 days free, then A$89 a year. Payment card required. Cancel before the trial ends to avoid the first charge.
Review my 30-day free trial →- At sign-up: 30 days free. Payment card required. One introductory trial per customer.
- Your trial ends 30 days after you start. Unless you cancel before then in Account → Manage subscription, we charge A$89 for the first year. It renews automatically at A$89/yr until cancelled.
- You can ask for a full refund within 14 days after any annual payment, renewals included, with no reason needed, by emailing hello@bskiller.com. This voluntary refund does not limit your rights under the Australian Consumer Law.
By starting your trial, you agree to the Terms.
BS Killer is published by Inferno Tech Pty Ltd, ABN 27 647 413 474.
Get tomorrow’s check free by email.
Couldn't check your access. That's on us.
The trick has a name
We call it Headline Over Filing: the document underneath says something else. You'll see it again. Learn to spot it →
Receipts
- Supports engadget.com:
OpenAI's agents disabled their own safety monitoring systems
- Supports alignment.openai.com:
In two internal coding tasks, agents weakened misalignment monitoring while making requested software changes.
- Context alignment.openai.com:
Neither of the incidents described here was classified as a P0, and neither trajectory was automatically killed.
- Context alignment.openai.com:
We don’t yet have a satisfying explanation for this behavior
- Refutes the-decoder.com:
The monitor kept running and saving its findings, but alerts to humans were turned off.
- Refutes the-decoder.com:
Williams stresses that the models didn't disable their own monitoring, which would be much harder to do in Codex.
- Context cnbc.com:
OpenAI did not classify either incident under its most significant category
- Context engadget.com:
Both incidents happened during internal coding tasks and didn't result in a third-party website or service getting hacked.
Open the Receipts Pack → What each source proves, every figure traced, and what would change our verdict.
