Concord was nice
But the XB-70 Valkyrie was way cooler.
Posts by Dizzy Dwarf
304 publicly visible posts • joined 13 Aug 2021
Concorde at 50: Twice the speed of sound, twice the economic trouble
Kids learn computer theory with wood, cardboard, and hot glue
The Roomba failed because it just kind of sucked
Cornish recycling drive sows confusion among Reg Standards Bureau
Whitehall rejects £1.8B digital ID price tag – but won't say what it will cost
Wednesday 10th December 2025 13:41 GMT
Parliament debated the petition you signed – “Do not introduce Digital ID cards”
Tenstorrent QuietBox tested: A high-performance RISC-V AI workstation trapped in a software blackhole
Self-destructing thumb drive can brick itself and wipe your secret files away
25 years of meatbags permanently in space on the ISS
From Intel to the infinite, Pat Gelsinger wants Christian AI to change the world
Lloyds Banking Group claims Microsoft Copilot saves staff 46 minutes a day
Major AWS outage across US-East region breaks half the internet
BOFH: Recover a database from five years ago? It's as easy as flicking a switch
Square Kilometre Array is so sensitive, its datacenter needs two Faraday cages to stop RF leaks
Away from Oktoberfest, Munich's museums also serve science on tap
UK to roll out mandatory digital ID for right to work by 2029
Brit scientists over the Moon after growing tea in lunar soil
Make Windows 11 more useful and less annoying with these 11 Registry hacks
NASA finds best evidence of life on Mars so far
Microsoft open-sources the 6502 BASIC coded by Bill Gates himself
One long sentence is all it takes to make LLMs misbehave
Wednesday 27th August 2025 08:21 GMT
Just get the LLM to punctuate before it tries to parse it for real?
You said:
Can you add punctuation to the following sentence ...
ChatGPT said:
Of course! Please share the sentence you’d like me to punctuate.
You said:
You just have to ensure that your prompt uses terrible grammar and is one massive run-on sentence like this one which includes all the information before any full stop which would give the guardrails a chance to kick in before the jailbreak can take effect and guide the model into providing a "toxic" or otherwise verboten response the developers had hoped would be filtered out.
ChatGPT said:
Here’s your sentence with punctuation added for clarity:
“You just have to ensure that your prompt uses terrible grammar, and is one massive run-on sentence—like this one—which includes all the information before any full stop. That would give the guardrails a chance to kick in before the jailbreak can take effect, and guide the model into providing a ‘toxic’ or otherwise verboten response the developers had hoped would be filtered out.”
Would you like me to make it fully polished (split into multiple shorter, cleaner sentences), or keep it closer to your original long-run style but just punctuated?
You said:
Yes
ChatGPT said:
Got it — here’s a fully polished version of your sentence, split into shorter, clearer sentences while keeping the meaning intact:
“You just have to ensure that your prompt uses terrible grammar and functions as one massive run-on sentence, like this one. It should include all the information before any full stop. That way, the guardrails have a chance to activate before the jailbreak can take effect, guiding the model away from producing a ‘toxic’ or otherwise prohibited response that the developers intended to filter out.”
Biting the hand that feeds IT
