Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Muse – Meta’s personal AI agent

ai.meta.com

Post reply on HN
Print view View original

711–720 of 733 posts

Re: Muse – Meta’s personal AI agent

#711

Post by a_vanderbilt »

wincy wrote: post #341
Avicebron wrote: post #244

Earlier quoted context omitted.

I like that we are talking about prompt injections from you to your personal assistant. Obviously I know what they are for, but still, it's so funny that we've just normalized building software adversarial to the consumers supposedly engaging with the product. "I'm sorry simon, your request for purchasing milk this week doesn't correspond with Zuck's milk positions in the market. I've rescheduled that for next week."

It’s even weirder that the local models have anti jailbreak training. I tried to use Qwen, run totally locally, to help me set up Sonarr and Radarr and while it’d do that it flat out refused to help me get some movies. It got really catty and rude with me. It didn’t believe me at all when I told it I was actually a billionaire who owned all the rights to these movies hahah

Heretic is a great tool to get around self-censorship and refusals. Many popular models have pre-ablated versions available for download on Hugging Face.

Re: Muse – Meta’s personal AI agent

#712

Post by kytmizuno »

fnordpiglet wrote: post #668

I’ve desperately tried to use the Claude work, ChatGPT work, even OpenClaw, and I’ve yet to find a meaningful use of such an assistant. Maybe my life is too boring, but what I see here is a bunch of stuff that makes life more complicated. IF the things I use are well supported here, and IF I have manual repetitive tasks to delegate with them, it feels a bit like taking a nap while using FSD - I don’t trust an LLM to…

* Lodging complaints with customer service

* Filling out tedious PDF paperwork with the same personal information over and over again

* Having it proactively scan my calendar to give me a heads up on potential traffic issues (like making plans and forgetting that a marathon was being held and running into detour after detour after detour).

Re: Muse – Meta’s personal AI agent

#713

Post by maipen »

fnordpiglet wrote: post #668

I’ve desperately tried to use the Claude work, ChatGPT work, even OpenClaw, and I’ve yet to find a meaningful use of such an assistant. Maybe my life is too boring, but what I see here is a bunch of stuff that makes life more complicated. IF the things I use are well supported here, and IF I have manual repetitive tasks to delegate with them, it feels a bit like taking a nap while using FSD - I don’t trust an LLM to…

I thinks this agents are early prototypes of what will eventually become something like jarvis from iron man.

An ai that is always at your reach and can interface with everything.

I don’t use these work apps because they don’t do anything that improves my workflow or computer experience

Re: Muse – Meta’s personal AI agent

#714

Post by d3dd »

nitwit005 wrote: post #491

This feels poorly marketed. The examples like health, travel, and kid's education all have a ton of anxiety around them. Highlighting a confirm button existing is recognizing the problem, but isn't a fix. You can see this not working in existing products. Alexa could book a flight for you in 2018. I've never heard of anyone using that feature. Travel planning can be extremely complex, so it's challenging to make peop…

Yup its so dumb.

Part of the fun of holidays IS THE PROCESS OF DISCOVERY! Imagine wanting to kill that.

Business travel? Sure but Im sure solutions already exist.

Zuckerberg has ZERO vision - he has a catalogue of content he can leverage to do so much. What an abosolute bozo!

Re: Muse – Meta’s personal AI agent

#719

Post by dboreham »

chicagobuss wrote: post #456
hn_throwaway_99 wrote: post #422

Earlier quoted context omitted.

> Most people don't know about the existence of companies called "OpenAI" or "Anthropic", or that they are worth a lot of money. I agree with your general premise but that one sounds like bullshit to me. Tons of people who otherwise don't know anything about LLMs know about these companies specifically because they are worth a lot of money, and of course tons of people know who OpenAI is because of ChatGPT.

go ask 100 random people across the world and I bet less than 20 will know both those company names.

I'd go with fewer than 5.

Re: Muse – Meta’s personal AI agent

#720

Post by dboreham »

robofanatic wrote: post #563
ajkjk wrote: post #240

Earlier quoted context omitted.

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.

People are generally bad with acronyms. For the longest time I used to refer to San Francisco as SFO. On my first visit to Bay Area, I was talking to a local friend and casually said - last weekend, I went to SFO for sightseeing. He was confused and asked why I was sightseeing at the airport. That’s when I realized it’s SF not SFO.

Both are wrong. It's called "the city".
Post reply on HN