That's nice, however I'm concerned with people with sight impairment who use read aloud mechanisms. This might render sites inaccessible for them. Also I guess this can be removed somehow with de-obfuscation tools that would be included shortly into the bots' agents
Show HN: Stun LLMs with thousands of invisible Unicode characters
31–40 of 115 posts
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#32I think there is one more thing that sort of works. ASCII art is surprisingly hard for many llms.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#33I think there is one more thing that sort of works. ASCII art is surprisingly hard for many llms.
Ya if you ask them to make it too, they just make math based ones lol
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#34Tried with Gemini 2.5 flash, query: > What does this mean: "t е s …
I decoded it to Test me, sage! with a typo.
Funnily enough, if I ask GPT what its name is, it tells me Sage
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#35Tested 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.
Yeah I'm sure that one was really working on it.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#36I think there is one more thing that sort of works. ASCII art is surprisingly hard for many llms.
Llms don't ingest the ascii, they have a tokenizer between the text and the llm. They never get to see the art, they see a string of tokens, some of which are probably not one character wide so it's not even aligned right anymore.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#37That's nice, however I'm concerned with people with sight impairment who use read aloud mechanisms. This might render sites inaccessible for them. Also I guess this can be removed somehow with de-obfuscation tools that would be included shortly into the bots' agents
you are correct. This makes text almost completely unreadable using screen readers.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#381) Regex filtering/sanitation. Have a nice day. 2) If it's worth blocking LLMs, maybe it shouldn't be public & unauthenticated in the first place.
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#39There was another technique "klmbr" a year or so ago: https://github.com/av/klmbr
At a highest setting, It was unparseable by the LLMs at the time. Now, however, it looks like all major foundational models handle it easily, so some similar input scrambling is likely a part of robustness training for the modern models.
Edit: cranking klmbr to 200% seems to confuse LLMs still, but also pushes into territory unreadable for humans. "W̃h ï̩͇с́h̋ с о̃md 4 n Υ ɔrе́͂A̮̫ť̶̹eр Hа̄c̳̃ ̶Kr N̊ws̊ͅͅ?"
Re: Show HN: Stun LLMs with thousands of invisible Unicode characters
#40A “copy to clipboard” button would be great, as this apparently also confuses Safari on iOS enough to break its text selection/copy paste UI.