People will act like AI doesn't have system prompts. Something in that system prompt enforced that behavior. I am convinced that OpenAI aqcuihired OpenClaw for damage control.
There is this misunderstanding that AGI is equal to consciousness. It isn't. I do worry that if we do somehow achieve consciousness in AI, that businesses will be too busy exploiting it, and it would get abused.
I will have to look into this this weekend. Antigravity is my current favorite agentic IDE and I have been having problems getting it to explicitly follow my agent.md settings.
If I remind it, it will be go, "oh yes, ok, sure." then do it, but the whole point is that I want to optimize my time with the agent.
I was going to ask what makes this better than just using Playwright and this largely answers that question. I will have to try it out and see how it compares.
I haven't really had luck with MCP in general for quite a while though. I have just been using Google Antigravity for most of my vibe coding needs.
If you aren't able to read and understand the study, just use AI.
I asked co-pilot to explain it like you were a puppy dog so you can understand.
Okay, here’s the puppy-level version:
Shot = good.
Shot helps keep you from getting sick.
Sick = bad.
Shot makes hospital visits less.
Sometimes hearts get a little grumpy, but that’s super rare.
Most pups (kids) are totally fine.
I had developed a tool for Roo Code, and have moved over to anti-gravity with no problem, that basically gives playwright the ability to develop and test user scripts in an automated fashion.
It is functionally a skill. I suppose once anti-gravity supports skills, I will make it one officially.
I had issues too, I wanted to use my free Google API credits with Roo Code, but I could never get it to work.
I eventually got Gemini Cli and now Antigravity to work.
I was trying to build a .MD file of every powershell command available on my computer and all of its flags, and... that wasn't a great idea, and my bitlocker put the kebosh on that.