Ever think your AI assistant might get tricked by a sneaky email? 👀 DeepMind just dropped a super interesting white paper showing how they're making Gemini 2.5 their most secure model yet, especially against something called indirect prompt injection. They’re using automated red teaming (basically attacking their own models constantly) to uncover weak spots, plus model hardening to help Gemini ignore shady, embedded instructions. The result? Gemini got way better at resisting attacks without hurting performance. 🤖💪 This matters a lot for those of us building automations with LLMs that interact with external data. As we keep connecting tools and letting AI assist with more sensitive tasks, security needs to evolve just as fast. If you’re building with LLMs and agent-like behavior, testing with adaptive attacks (not just static ones) should be part of your process. Read the full article here: https://deepmind.google/discover/blog/advancing-geminis-security-safeguards

Hi I am new to Make and I am not sure if I should get the core or the Pro subscription. I am planning on integrating GHL with other apps and so, I would like to know your opinion. Thanks in advance

What is the difference between n8n , make , monday , heighlevel .. and this kind of tools ?

Here is a new video for you guys! You can view it here or in the No-Code Automation course found in the Classroom tab.

Is there is any way to feed whole data from airtable sheet to gpt?