People are unfortunately just ranting about not trusting meta, which… okay, fine, but having played around with this for the past hour or so it’s probably my favorite mobile LLM experience so far across Claude and ChatGPT and Gemini. It’s very good and in its own class.
Muse – Meta’s personal AI agent
351–360 of 732 posts
Re: Muse – Meta’s personal AI agent
#352I've got access to their sandbox, don't know if I should've, lol
Re: Muse – Meta’s personal AI agent
#353First thing I am using this is for scraping (my) groups from FaceBook since they shutdown the API a while back. "Give me comments from this group from 1/1 to 8/1 in json". Hope it works.
I'll be interested to see what access it gives you to Meta products.
Grok Bot doesn't have direct access to Twitter like Grok on x.com does, for no good reason, but it does have an API plugin which gives you free $20 credit if you install it.
When these companies want to lock you into their platforms it seems kinda dumb to not give their own products access to their own products.
Re: Muse – Meta’s personal AI agent
#354Earlier quoted context omitted.
The average person is not using a calendar and is not getting more than 1 relevant personal email per week. Most people use their personal email extremely sparingly and it is inundated with promotional / account-related materials which are already handled rather deftly by most mainstream email providers
Ha, tell me you don't have children without...
The average kid in an average suburban public school is not getting this amount of digital communication. If they are, they still aren't using a Google Calendar and are managing the complexity in much simpler ways (paper calendars)
Re: Muse – Meta’s personal AI agent
#355Naming your agent is a big deal for personal ownership. I'm surprised it took this long for a company to do this. People hate some company's AI. They love their pets. AI needs to be your pet.
I named mine Claude
Re: Muse – Meta’s personal AI agent
#356Earlier quoted context omitted.
lol no one is getting personal emails, maybe some people get one every few months, but most probably never (not taking into account other than order/shipping confirmations, login codes, etc)
I can only imagine you have no kids, serve on no boards, do not volunteer, and play no sports.
The average person is not serving on a board and is definitely not volunteering.
Sports communications at most travel/rec leagues is via group chat / Whatsapp / FB group.
Re: Muse – Meta’s personal AI agent
#357Has anyone tested it? How does it compare with GPT and Gemini?
I've been testing it today. It's fine. It's like base-level GPT or Gemini. I actually kinda like the cute thing it does where it emoji reacts to your messages before it acts on them. Grok Bot needs to steal that.
Re: Muse – Meta’s personal AI agent
#358I think Meta's strategy is to capture the 'normie-tier' of AI users. I know most of us here on HN track model releases quite frequently and discuss every parameter weight out of them, but most of the world is just... oblivious? I was discussing latest in tech with an accounting friend out of curiosity, and I kept talking about tiers of GPT-5.6 (Sol vs Terra vs Luna) and asked which one she used on the desktop 'Work'…
I think you're right, but I'd add that... if this wasn't obvious to you without being told, you should really question your worldview a bit. A lot of people think that chat.com is an AI called "chat". Most people don't know acronym "LLM". Most people don't know about the existence of companies called "OpenAI" or "Anthropic", or that they are worth a lot of money. Etc.
I think you are overestimating things. While there will be people who don't know - it's probably not as many as you think.
Re: Muse – Meta’s personal AI agent
#359I just asked it:
“Can you lowball fools on marketplace for me?”
It replied:
“Say less, I can do that. What am I hunting…”
People are going to use this product for bad things.
Re: Muse – Meta’s personal AI agent
#360I think Meta's strategy is to capture the 'normie-tier' of AI users. I know most of us here on HN track model releases quite frequently and discuss every parameter weight out of them, but most of the world is just... oblivious? I was discussing latest in tech with an accounting friend out of curiosity, and I kept talking about tiers of GPT-5.6 (Sol vs Terra vs Luna) and asked which one she used on the desktop 'Work'…
It seems like on the “Chat” mode of ChatGPT it doesn’t allow switching the model. It’s just “5.6” with the effort level