Give your tired old AI LLM chatbot a new lease of life! Copy your old, slow, token-heavy chat into https://www.prunejuice.me - compress it, copy into a new chat and that old slow LLM will be up and running with renewed vigour! And it will even remember what you were talking about! (just add the current dictionary to your project knowledge documents for better comprehension).

This was a fun project - feel free to support a good cause fighting against logorrhoea and token pollution! Buy prunes!

PS. It runs entirely client-side (i.e.via Javascript in your browser), so in theory it's completely private - no sinister back-end or retention your data. I'll release the opensource version soonish. Cheers!

"Within the Meta AI app, a “discover” tab shows a timeline of other people’s interactions with the chatbot; a short scroll down on the Meta AI website is an extensive collage. While some of the highlighted queries and answers are innocuous—trip itineraries, recipe advice—others reveal locations, telephone numbers, and other sensitive information, all tied to user names and profile photos."

Oh no.

https://www.wired.com/story/meta-artificial-intelligence-chatbot-conversations/

New AI Security Risk Uncovered in Microsoft 365 Copilot

A zero-click vulnerability has been discovered in Microsoft 365 Copilot—exposing sensitive data without any user interaction. This flaw could allow attackers to silently extract corporate data using AI-integrated tools.

If your organization is adopting AI in productivity platforms, it’s time to get serious about AI risk management:
• Conduct a Copilot risk assessment
• Monitor prompt histories and output
• Limit exposure of sensitive data to AI tools
• Update your incident response plan for AI-based threats

AI can boost productivity, but it also opens new doors for attackers. Make sure your cybersecurity program keeps up. Contact our LMG Security team if you need a risk assessment or help with AI policy development.

Read the article: https://www.bleepingcomputer.com/news/security/zero-click-ai-data-leak-flaw-uncovered-in-microsoft-365-copilot/

chatbetter is an AI application that sends your prompt off to 3 different LLMs at the same time: Anthropic Claude 3.7 Sonnet, Google Gemini 2.5 Flash, and Meta Llama 4 Maverick. It has a free tier and a paid tier that I don't think you would need unless you were a company. It seems that the composite answer is better than what you would get using a single LLM like OpenAI's ChatGPT (unless you want an answer with complex visual diagrams).

https://app.chatbetter.com

AI is the new attack surface—are you ready?

From shadow AI to deepfake-driven threats, attackers are finding creative ways to exploit your organization’s AI tools, often without you realizing it.

Watch our new 3-minute video, How Attackers Target Your Company’s AI Tools, for advice on:

The rise of shadow AI (yes, your team is probably using it!)
Real-world examples of AI misconfigurations and account takeovers
What to ask vendors about their AI usage
How to update your incident response plan for deepfakes
Actionable steps for AI risk assessments and inventories

Don’t let your AI deployment become your biggest security blind spot.

Watch now: https://youtu.be/R9z9A0eTvp0