The company tested 123 cases representing 29 different attack scenarios and found a 23.6 percent attack success rate when browser […]
Category: Simon Willison
New Grok AI model surprises experts by checking Elon Musk’s views before answering
Seeking the system prompt Owing to the unknown contents of the data used to train Grok 4 and the random […]
Anthropic summons the spirit of Flash games for the AI age
Skip to content AI chatbot codes browser-based apps from plain English with classic web vibes. On Wednesday, Anthropic announced a […]
Microsoft surprises MS-DOS fans with remake of ancient text editor that works on Linux
Last month, Microsoft released a modern remake of its classic MS-DOS Editor, bringing back a piece of computing history that […]
Hidden AI instructions reveal how Anthropic controls Claude 4
Willison, who coined the term “prompt injection” in 2022, is always on the lookout for LLM vulnerabilities. In his post, […]
Researchers claim breakthrough in fight against AI’s frustrating security hole
99% detection is a failing grade Prompt injections are the Achilles’ heel of AI assistants. Google offers a potential fix. […]
Meta’s surprise Llama 4 drop exposes the gap between AI ambition and reality
Meta constructed the Llama 4 models using a mixture-of-experts (MoE) architecture, which is one way around the limitations of running […]
Anthropic’s new AI search feature digs through the web for answers
Caution over citations and sources Claude users should be warned that large language models (LLMs) like those that power Claude […]
Why extracting data from PDFs is still a nightmare for data experts
Optical Character Recognition Countless digital documents hold valuable info, and the AI industry is attempting to set it free. For […]