RSSAmplifier

Blog

Essays

Hello World...

kaindume.bearblog.devRSS feed ↗2 posts

Latest posts

LLMinate - LLM CAPTCHA System

Detecting LLMs with Word Substrings: A Novel Approach to CAPTCHA How a simple linguistic insight can help distinguish humans from AI The Insight Here's an observation: when asked to generate random nonsense words, humans and AI behave completely differently . Humans mash keyboards: ksdjsdksdk , eokdfweinfhfejla , owiewewlkdfk Large Language Models generate plausible-sounding nonsense: Vesperthrum…

Fallacy of Decentralization

Decentralized networks work well when everyone is following the protocol. But there are always bad actors in large decentralized networks, they attack the protocol or attack other network participants. Traditionally the way you mitigate this is by adding a sub-system to filter out the bad actors. This sub-system than ends up with so much power it centralizes the network. Another way to solve it is…