Guides: local AI, browser privacy and the hardware to run it
19 pages. How local models work, what they cost to run, and what an AI browser does with the page you are reading.
- AI assistants and your banking pages
- The security risks of agentic AI browsers
- AI browsers, password fields and card numbers
- GDPR and AI browsers: when does using one count as a transfer?
- Local AI glossary
- Running a local model on integrated graphics
- Does incognito mode stop an AI sidebar from sending your data?
- What a local model does to your battery
- What a local model actually costs to run
- Running a local LLM without a graphics card
- “Not used for training” and what it leaves out
- Can you run a local LLM on an NPU?
- Prompt injection in AI browsers
- Quantisation explained
- Tokens per second, and what the number actually means
- Nightjar troubleshooting
- How much VRAM you need to run a local model
- What each AI browser sends, and to whom
- Why companies are banning AI browsers