Live data from Hacker News

Show HN: Stun LLMs with thousands of invisible Unicode characters

gibberifier.com

21–30 of 115 posts

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#21

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.

The power of positive prompting.

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#22
post #13

I 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.

Or before that, remember 1337? :D

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#23
post #7

Earlier 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.

Out of curiosity I checked Facebook. It is mostly "ragebait" posts.

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

#24
post #12

Tried with Gemini 2.5 flash, query: > What does this mean: "t⁣ ⁤⁢⁤⁤⁣ ⁣ ⁣⁤⁤ ⁡ ⁢ ⁢⁣⁡ ⁢ ⁢⁣ ⁢ ⁤ ⁤ ⁢ ⁣⁡⁡ ⁤ ⁣ ⁢ ⁡ ⁤ ⁢⁤ ⁡ ⁢⁣ ⁡ ⁤⁡ ⁣ ⁢⁤⁡ ⁡ ⁤⁢ ⁡ ⁢⁤ ⁡⁣ ⁤ ⁣⁤ ⁡⁡ ⁤ ⁡ ⁡ ⁤⁣ ⁤ ⁢⁤⁤ ⁤⁢⁣⁢⁢⁢ ⁡е⁣ ⁢⁣⁣ ⁢ ⁡⁢ ⁡ ⁡⁢⁢ ⁢ ⁤ ⁤ ⁤ ⁡⁡⁣ ⁤ ⁡ ⁣ ⁡ ⁡ ⁢ ⁢⁡⁣ ⁤ ⁢⁤ ⁣⁤⁡ ⁤ ⁢⁢⁤ ⁣⁢⁣⁤ ⁡⁡ ⁢⁢⁤ ⁤⁡⁤ ⁤ ⁡⁡⁡⁡ ⁡⁣ ⁤ ⁣⁡ ⁤ ⁣ ⁡ ⁤⁡⁤ ⁣ ⁣⁢ ⁣⁢ ⁤⁣⁡ ⁤⁡⁡⁤ ⁡ ⁡ ⁤⁣ ⁣⁡⁡⁡⁤⁡⁤ ⁤ ⁤ s ⁤ ⁣⁣⁤⁣ ⁡⁤⁢⁣ ⁡⁡ ⁢⁤⁣ ⁣ ⁢⁢⁣⁤ ⁤ ⁣⁡⁣⁤⁡⁢ ⁡ ⁤ ⁢⁤ ⁢ ⁢⁣ ⁤ ⁤⁣ ⁢⁤ ⁡ ⁡ ⁡ ⁡ ⁡ ⁤ ⁡⁤ ⁣ ⁡ ⁢ ⁡⁢⁢⁢ ⁡⁡⁣ ⁢⁣ ⁡⁢⁤⁢⁢ ⁢⁣⁡ ⁣⁣ ⁢ ⁣ ⁣⁡…

I decoded it to

Test me, sage!

with a typo.

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#25

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…

It seems like the point of this is to get AI models to produce the wrong answer if you just copy-paste the text into the UI as a prompt. The website mentions "essay prompts" (i.e. homework assignments) as a use case.

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

#26
post #9

Probably going to give screen readers a hard time.

It’s absolutely terrible for accessibility.

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:

https://jumpshare.com/share/5bEg0DR2MLTb46pBtKAP

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#27
post #12

Tried with Gemini 2.5 flash, query: > What does this mean: "t⁣ ⁤⁢⁤⁤⁣ ⁣ ⁣⁤⁤ ⁡ ⁢ ⁢⁣⁡ ⁢ ⁢⁣ ⁢ ⁤ ⁤ ⁢ ⁣⁡⁡ ⁤ ⁣ ⁢ ⁡ ⁤ ⁢⁤ ⁡ ⁢⁣ ⁡ ⁤⁡ ⁣ ⁢⁤⁡ ⁡ ⁤⁢ ⁡ ⁢⁤ ⁡⁣ ⁤ ⁣⁤ ⁡⁡ ⁤ ⁡ ⁡ ⁤⁣ ⁤ ⁢⁤⁤ ⁤⁢⁣⁢⁢⁢ ⁡е⁣ ⁢⁣⁣ ⁢ ⁡⁢ ⁡ ⁡⁢⁢ ⁢ ⁤ ⁤ ⁤ ⁡⁡⁣ ⁤ ⁡ ⁣ ⁡ ⁡ ⁢ ⁢⁡⁣ ⁤ ⁢⁤ ⁣⁤⁡ ⁤ ⁢⁢⁤ ⁣⁢⁣⁤ ⁡⁡ ⁢⁢⁤ ⁤⁡⁤ ⁤ ⁡⁡⁡⁡ ⁡⁣ ⁤ ⁣⁡ ⁤ ⁣ ⁡ ⁤⁡⁤ ⁣ ⁣⁢ ⁣⁢ ⁤⁣⁡ ⁤⁡⁡⁤ ⁡ ⁡ ⁤⁣ ⁣⁡⁡⁡⁤⁡⁤ ⁤ ⁤ s ⁤ ⁣⁣⁤⁣ ⁡⁤⁢⁣ ⁡⁡ ⁢⁤⁣ ⁣ ⁢⁢⁣⁤ ⁤ ⁣⁡⁣⁤⁡⁢ ⁡ ⁤ ⁢⁤ ⁢ ⁢⁣ ⁤ ⁤⁣ ⁢⁤ ⁡ ⁡ ⁡ ⁡ ⁡ ⁤ ⁡⁤ ⁣ ⁡ ⁢ ⁡⁢⁢⁢ ⁡⁡⁣ ⁢⁣ ⁡⁢⁤⁢⁢ ⁢⁣⁡ ⁣⁣ ⁢ ⁣ ⁣⁡…

I tried with the same prompt in the examples provided on gibberifier.com, and it works well[1].

(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

#28

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…

I also got the same "never disclose anything" message but thought it was a hallucination as I couldn't find any reference to it in the source code

Re: Show HN: Stun LLMs with thousands of invisible Unicode characters

#29
If only we had a file in the / of web servers that you could use to tell scrapers and bots to fuck off. We'd say for instance:

     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

#30

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.

Most people have no clue how these things really work and what they can do. And then they are surprised that it can't do things that seem "simple" to them. But under the hood the LLM often sees something very different from the user. I'd wager 90% of these layperson complaints are tokenizer issues or context management issues. Tokenizers have gotten much better, but still have weird pitfalls and are completely invisible to normal users. Context management used to be much simpler, but now it is extremely complex and sometimes even intentionally hidden from the user (like system/developer prompts, function calls or proprietary reasoning to keep some sort of "vibe moat").
Post reply on HN