Aaronson

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

20:27

2026-08-21

promptcube3.com

artificial-intelligence

Watermarked AI text still fools most readers in blind tests

A new study finds that watermarked AI text fools most readers in blind tests, with only 53% of participants correctly identifying watermarked LLM output as AI versus 51% for unwatermarked LLM output, …

23:16

2026-08-13

declaude.org

artificial-intelligence

How AI text watermarking works

Google has watermarked text from its Gemini app and web experience since 2024, and as of August 2026, new Claude models from Anthropic mark text at the model level, using a statistical method that hid…

// co-occurs with top 8 entities

Kirchenbauer 2 Google 1 Gemini 1 Anthropic 1 Claude 1 SynthID 1 OpenAI 1 Llama-3 1

// topics top 5 topics

artificial intelligence 2 ai research 2 large language models 1 ai tools 1 ai safety 1