Why did summarizing a web page need access to so many browser functions? How does scanning the user's emails without confirmation result in being able to provide a better summary? It seems way to risky to do.
Edit: From the blog post for possible regulations.
>The browser should distinguish between user instructions and website content
>The model should check user-alignment for tasks
These will never work. It's embarrassing that these are even included, considering how models are always instantly jailbroken the moment people get access to them.
We’re in the “SQL injection” phase of LLMs: control language and execution language are irrecoverably mixed.
Well said.
> Why did summarizing a web page need access to so many browser functions?
Relax man, go with the vibes. LLMs need to be in everything to summarize and improve everything.
> These will never work. It's embarrassing that these are even included, considering how models are always instantly jailbroken the moment people get access to them.
Ah, man you are not vibing enough with the flow my dude. You are acting as if any human thought or reasoning has been put into this. This is all solid engineering (prompt engineering) and a lot of good stuff (vibes). It's fine. It's okay. Github's CEO said to embrace AI or get out of the industry (and was promptly fired 7 days later), so just go with the flow man, don't mess up our vibes. It's okay man, LLMs are the future.
Beside the security issue mentioned in a sibling post, we're dealing with tools that have no measure of their token efficiency. AI tools today (browsers, agents, etc.) are all about being able to solve the problem, with short thrift paid to their efficiency. This needs to change.
probably vibe coded
There were bad developers before there was vibe coding. They just have more output capacity now and something else to blame.
One thing about LLMs is they effectively gave bad developers superpowers. I think it’s going to usher in a new golden era for cybersecurity experts and consultancies. The whole side of the tech industry that involves cleaning up a mess.
The fact that we're N years in and the same "why don't you just fix it with X" proposals are still being floated... Is kind of depressing.