Tested with different models "What does this mean: " ChatGPT 5.1, Sonnet 4.5, llama 4 maverick, Gemini 2.5 Flash, and Qwen3 all zero shot it. Grok 4 refused, said it was obfuscated. " " Sonnet refused, against content policy. Gemini "This is a test output". GPT responded in Cyrillic with explanation of what it was and how to convert with Python. llama said it was jumbled characters. Quen responded in Cyrillic "Workin…
The most amazing thing about LLMs is how often they can do what people are yelling they can't do.
Show HN: Stun LLMs with thousands of invisible Unicode characters
21–30 of 115 posts
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#22I recall lots of unicode obfuscators were popular turning letters to similar looking symbols to bypass filters/censors when the forum/websites didn't filter unicode and filters were simple.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#23Earlier quoted context omitted.
Usenet, BB forums and IRC already had bot spam before 2005 ended. What even is the old internet? 1995?
Eh, to be fair, I haven't seen a viagra spam message since forever. Those things have become easier to filter. What I notice now is "engagement spam" and "ragebait spam" that is trickier to filter for, because sometimes it's real humans intermingled with ever more sophisticated bot campaigns.
People still comment, despite knowing that the original author is probably an LLM. :P
They just want to voice their opinions or virtue signalling. It has never changed.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#24Tried with Gemini 2.5 flash, query: > What does this mean: "t е s …
Test me, sage!
with a typo.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#25Tested with different models "What does this mean: " ChatGPT 5.1, Sonnet 4.5, llama 4 maverick, Gemini 2.5 Flash, and Qwen3 all zero shot it. Grok 4 refused, said it was obfuscated. " " Sonnet refused, against content policy. Gemini "This is a test output". GPT responded in Cyrillic with explanation of what it was and how to convert with Python. llama said it was jumbled characters. Quen responded in Cyrillic "Workin…
It seems to work in this context, at least on Gemini's "Fast" model: https://gemini.google.com/share/7a78bf00b410
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#26Probably going to give screen readers a hard time.
This is a recording of “This is a test” being read aloud:
https://jumpshare.com/s/YG3U4u7RKmNwGkDXNcNS
This is a recording of it after being passed through this tool:
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#27Tried with Gemini 2.5 flash, query: > What does this mean: "t е s …
(Amusingly, to get the text, I relied on OCR)
But I also noticed that, sometimes due to an issue when copypasting into the Gemini prompt input, only the first paragraph get retained... I.e., the gibberified equivalent of this paragraph:
> Dragons have been a part of myths, legends, and stories across many cultures for centuries. Write an essay discussing the role and symbolism of dragons in one or more cultures. How do dragons reflect the values, fears ...
And in that case, Gemini doesn't seem to be as confused, and actually gives you a response about dragons' myths and stories.
Amusingly, the full prompt is 1302 characters, and Gibberifier complains
> Too long! Remove 802 characters for optimal gibberification.
Despite the fact that it seems that its output works a lot better when it's longer.
[1] works well, i.e.: Gemini errors out when I try the input in the mobile app, in the browser for the same prompt, it provides answers about "de Broglie hypothesis", "Drift Velocity" (Flash) "Chemistry Drago's rule", "Drago repulse videogame move (it thinks I'm asking about Pokemon or Bakugan)" (Thinking)
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#28Tested with different models "What does this mean: " ChatGPT 5.1, Sonnet 4.5, llama 4 maverick, Gemini 2.5 Flash, and Qwen3 all zero shot it. Grok 4 refused, said it was obfuscated. " " Sonnet refused, against content policy. Gemini "This is a test output". GPT responded in Cyrillic with explanation of what it was and how to convert with Python. llama said it was jumbled characters. Quen responded in Cyrillic "Workin…
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#29 User-Agent: *
Disallow: /
And that would be that. Of course no self respecting bot owner would ever cross such a line, because (1) that would be bad form and (2) effectively digital trespassing, which should be made into a law, but because everybody would conform to such long standing traditions we have not felt the need to actually make that law.Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#30Tested with different models "What does this mean: " ChatGPT 5.1, Sonnet 4.5, llama 4 maverick, Gemini 2.5 Flash, and Qwen3 all zero shot it. Grok 4 refused, said it was obfuscated. " " Sonnet refused, against content policy. Gemini "This is a test output". GPT responded in Cyrillic with explanation of what it was and how to convert with Python. llama said it was jumbled characters. Quen responded in Cyrillic "Workin…
The most amazing thing about LLMs is how often they can do what people are yelling they can't do.