The privacy issue blocks me from adopting this or other personal assistants: do I want to give muse my identity data and access to my mail, calendar, and phone so it can do even basic tasks like make appointments or pay bills?
It will be interesting to see if muse's privacy features can get users over this.
I agree, most of the proactive agent assistance use cases requires me to give out data I’m hesitant to give like email, financial data, health data…
I’m hoping someone makes a lower maintenance version of open source Muse or Grokbot or Dots (more user friendly than OpenClaw or Hermes) that I can easily deploy to my own AWS, Cloudflare, Vercel, or Fly account and use some ZDR friendly inference provider like Fireworks.
There was a run on Mac Mini's for people running OpenClaw earlier this year. I was doing some research earlier today on an idea and that came up as an option because it (and Apple's hardware for Macs) have shared RAM across CPU and GPU so its apparently a viable option to run ollama (ironically from Meta) or other local models for simple tasks.
I think VPS are going to be expensive because of the RAM and GPU requirements - 32GB RAM is beefy for a VPS and might run like $30/month on the cheap end. Thats $360/year so running something at home might be more secure, capable and cheaper. Remote/mobile access might be viable with something like tailscale.
It's funny that you say you want a more user-friendly lower maintenance version of something than Muse but then say something better than openclaw or Hermes.
What exactly is high maintenance about Hermes? I agree the setup could be a little more user-friendly, but I have it running on my VPS with Matrix and the actual maintenance has been very minimal.
Spending a lot of time on harness engineering to try to compensate for deficiencies with Deepseek v4 flash because I'm too cheap to use better models on the other hand...
A lot of use cases for agents require long running sessions. And you're likely to have many agent sessions running in parallel. These aren't going to be running on your personal devices
Why not? Why wouldn't your phone be able to do this?
The other advantage long running sessions have is that very low tok/s are perfectly acceptable. In fact, hardly noticeable.
(aside, of course, from Google and Apple both having incentives to prevent this from happening, as both depend on selling centralized services to you and advertisers, and the local model breaks both)
I agree. I currently do run a bunch of dev containers on my local Docker but that is not good enough, they neeed to be able to work while I am on the run and close my laptop. So we are trying having personal containers on a managed Kibernetes cluster for every developer. We’re still working on making this work but it seems promising, the hardest thing being just permissions to let the agent use MCP servers, http APIs etc. If anyone has done this, how did you manage that?? I know there are products like OpenCLI that help with the problem but we want something we can build ourselves since AI makes it so much easier to build things!
Use ai to build it a poc and read the code after, learn, rebuild until you find something that works.
I host all of my custom applications on a machine in my home with Tailscale, k8, infrastructure as code
It’s wired, always on, has access to my gpu running on another machine or falls back to cloud inference
Self hosted GitHub action runners on each different platform for build/deploy of various projects: tauri v2, apis, web uis, native macOS apps, Unity 3d
None of this existed a month ago and it’s been a blast pretending to run my own platform
Durability and parallelism aren't that hard, and you won't be needing frontier models for much of this stuff. The parameter efficiency of models is increasing rapidly. I don't see why a (near-)future device wouldn't be capable of running a perfectly capable personal assistant.
My personal solution to this is to run DSH in an Incus VM on a local machine, then expose the web UI to the internet through my VPS (with some extra auth). I also made a couple of UI tweaks so it works better as a PWA.
Now I have persistent chats and a persistent environment that I can talk to from any device, including my phone. Even have X11 + CUA + Chromium inside the VM so the agent can use a real browser for sites that require it. DSH bwrap is the first layer of containment, VM is the second layer. I can swap between API models and local inference with a drop-down in the UI.
I realise this is way more setup than Meta's customers would tolerate, but the HN crowd could slap something together quite quickly. Using a coding agent with a nice chat UI as your general chat client is surprisingly smooth: just create an empty workspace.
I think Muse is the right shape in a lot of ways but I come unstuck at the point where my personal details and credentials are inside the VM.
I’m sure there is probably a skunkworks like team secretly working at Apple trying to make the hardware needed to accelerate local models enough to handle personal data processing needs without decimating the battery. I’d guess another team is probably tasked at researching a E2E encrypted remote inference mechanism where the personal data that does get out of the iPhone/ipad/Mac is encrypted with something Secure Enclave on processor, and “even Apple can’t read it”..
Apple is my long term bet for personal AI computing.
No way in hell am I letting FaceBook/OpenAI/Anthropic/Deepseek/anybody have complete access to my personal digital life. That’s just dumb.
Just look at OpenAI digging through ChatGPT logs to get the idea to solve the math problems etc. I’m sure all the subscription plans and subsidies are aimed at gathering enough breadth of real people comms to get the models to improve on wider signals…
Worst case, I don’t want to be voluntarily giving up my digital footprint to get profiled a certain way and be fed what AI overlords (or the companies that wield them really) think I should get as an answer/response.
My thoughts and activity stays private as much as practical and feasible.
> where the personal data that does get out of the iPhone/ipad/Mac is encrypted with something Secure Enclave on processor, and “even Apple can’t read it”..
there already is technology for this, which is Confidential Computing which is implemented on Nvidia etc.
it requires transparency to audit it properly and if there's an exploit which weakens it then the security guarantees fall apart
but in terms of commercial viability, it's the most promising way to tackle this and it seems like Apple is already pushing for it with their Private Cloud Compute
> I’d guess another team is probably tasked at researching a E2E encrypted remote inference mechanism where the personal data that does get out of the iPhone/ipad/Mac is encrypted with something Secure Enclave on processor, and “even Apple can’t read it”..
That’s already in production. Look for Apple Private Cloud Compute
They are that good now. The computer is just too expensive. The computer is too expensive because of meta, openai, anthropic, grok, etc. it's funny how this works...
Absolutely. None of these tools are actually valuable unless you are down with all of your data being used against your interests short and long term.
"I can answer my emails 30s faster!" Cool but now meta knows everyone in your family's status, the bills you have, the Drs appts you have, your families health status, who services your loans, the emails you open the ones you don't, etc. it's a wet dream for surveillance capitalism and the mic subsidized by ignorant customers.
Meta's active user base doesn't care about privacy.
Most personal tasks take trivial amounts of time these days. Does a 5th grade teacher or an auto mechanic need a personal assistant? Do we need to be able to book a trip faster? It feels very gimmicky to me, but I realize I'm not their target audience.
Given that, I do think Meta will probably get the lions share of B2C AI and they have a proven track record of using personal data to serve ads and make a lot of profit. If they capture more of their user base's time, it keeps them engaged and away from a list of competitors. If Meta starts crushing it in this fashion I could see IPO's of OpenAI and Anthropic land like fart in church.
I mean I just used muse to plan out my entire weekend trip to Vegas recently. I booked everything myself but I asked it to shortlist dining options for me given dietary restrictions, events given restrictions (with elderly family), etc. it basically handled all the stuff I would have normally just Google searched for. Plus it made a nice web app dashboard to display it all. It seems pretty useful for common use.
It also handled payment splitting. I told it what person x spent for the group split 3 ways (it originally split by the total number of people, but I clarified that only me + x + y are paying) and it kept running totals. When I got an email from Venmo saying x sent me money, muse automatically updated the balance sheet.
We saw some signs written in an unfamiliar language. Muse told me what language it was.
I've been "forced" to use AI in my work since this year, but I only started experimenting with it with my own ChatGPT subscription recently. I'm able to afford $20/mo and I'm fine paying it. The average user meta is targeting wants a free assistant to replace Siri, which is what muse is.
Continuing my thought, talking to Muse and ChatGPT feel fundamentally different. The single thread chat Muse offers encourages you to talk to it like a person imo. But that's probably just me.
I think some of those tasks are part of the fun of a trip - doing the research on locations, events, restaurants, etc. You stumble through a bunch of things and little nuggets of that sit in your brain and then when you're on the trip they might come up - one place is abruptly closed, something looks like a bummer in person, etc. Without doing that research yourself then on the trip you have a list of things and aren't really knowledgable about alternatives.
Like I said, I'm not the target audience for a personal assistant. That does sound like a more ideal UX than what chat gippity and the others offer though. I would expect that with Meta - they really get the UX mostly right for people.
Sure, I get that. For this particular case, I've been to Vegas (family lives there) "plenty" so I don't really care much about stumbling upon stuff like you pointed out. I just wanted to have some places on hand to suggest for dinner and things to do when the group when we'd inevitably get to the "so can someone decide what are we doing for dinner???" part of the day. For planning a long trip to say Tokyo (never been) for vacation I'd do the regular stuff searching Google and reading blogs, but I'd also add AI search to it, if anything to find the current new "viral/trendy" stuff that I absolutely do not keep up with.
Yes we do care and many of us have set the privacy settings to certain things over the years
But this is where friends are and don't give me 'you could just call them'
Not everyone has access to email/phone. Facebook should work in theory, if they weren't so enthusiastic about intentionally eroding privacy (physically changing the privacy options). Multicast. I post some status to multiple people at once. I can find people I don't already know/have lost touch with, and connect with them
What Meta does, does not mean its users don't care and I wish you people would stop saying that
egl2020 · · focus · HN ↗
It will be interesting to see if muse's privacy features can get users over this.
mistercheese · · focus · HN ↗
I’m hoping someone makes a lower maintenance version of open source Muse or Grokbot or Dots (more user friendly than OpenClaw or Hermes) that I can easily deploy to my own AWS, Cloudflare, Vercel, or Fly account and use some ZDR friendly inference provider like Fireworks.
mattbrewsbytes · · focus · HN ↗
I think VPS are going to be expensive because of the RAM and GPU requirements - 32GB RAM is beefy for a VPS and might run like $30/month on the cheap end. Thats $360/year so running something at home might be more secure, capable and cheaper. Remote/mobile access might be viable with something like tailscale.
shostack · · focus · HN ↗
What exactly is high maintenance about Hermes? I agree the setup could be a little more user-friendly, but I have it running on my VPS with Matrix and the actual maintenance has been very minimal.
Spending a lot of time on harness engineering to try to compensate for deficiencies with Deepseek v4 flash because I'm too cheap to use better models on the other hand...
rienbdj · · focus · HN ↗
raz32dust · · focus · HN ↗
spwa4 · · focus · HN ↗
The other advantage long running sessions have is that very low tok/s are perfectly acceptable. In fact, hardly noticeable.
(aside, of course, from Google and Apple both having incentives to prevent this from happening, as both depend on selling centralized services to you and advertisers, and the local model breaks both)
brabel · · focus · HN ↗
devrwoody · · focus · HN ↗
I host all of my custom applications on a machine in my home with Tailscale, k8, infrastructure as code
It’s wired, always on, has access to my gpu running on another machine or falls back to cloud inference
Self hosted GitHub action runners on each different platform for build/deploy of various projects: tauri v2, apis, web uis, native macOS apps, Unity 3d
None of this existed a month ago and it’s been a blast pretending to run my own platform
ctolsen · · focus · HN ↗
wren6991 · · focus · HN ↗
Now I have persistent chats and a persistent environment that I can talk to from any device, including my phone. Even have X11 + CUA + Chromium inside the VM so the agent can use a real browser for sites that require it. DSH bwrap is the first layer of containment, VM is the second layer. I can swap between API models and local inference with a drop-down in the UI.
I realise this is way more setup than Meta's customers would tolerate, but the HN crowd could slap something together quite quickly. Using a coding agent with a nice chat UI as your general chat client is surprisingly smooth: just create an empty workspace.
I think Muse is the right shape in a lot of ways but I come unstuck at the point where my personal details and credentials are inside the VM.
jayd16 · · focus · HN ↗
reacharavindh · · focus · HN ↗
Apple is my long term bet for personal AI computing.
No way in hell am I letting FaceBook/OpenAI/Anthropic/Deepseek/anybody have complete access to my personal digital life. That’s just dumb.
Just look at OpenAI digging through ChatGPT logs to get the idea to solve the math problems etc. I’m sure all the subscription plans and subsidies are aimed at gathering enough breadth of real people comms to get the models to improve on wider signals…
Worst case, I don’t want to be voluntarily giving up my digital footprint to get profiled a certain way and be fed what AI overlords (or the companies that wield them really) think I should get as an answer/response.
My thoughts and activity stays private as much as practical and feasible.
r_lee · · focus · HN ↗
there already is technology for this, which is Confidential Computing which is implemented on Nvidia etc.
it requires transparency to audit it properly and if there's an exploit which weakens it then the security guarantees fall apart
but in terms of commercial viability, it's the most promising way to tackle this and it seems like Apple is already pushing for it with their Private Cloud Compute
wrxd · · focus · HN ↗
That’s already in production. Look for Apple Private Cloud Compute
thatsabadlook · · focus · HN ↗
thatsabadlook · · focus · HN ↗
"I can answer my emails 30s faster!" Cool but now meta knows everyone in your family's status, the bills you have, the Drs appts you have, your families health status, who services your loans, the emails you open the ones you don't, etc. it's a wet dream for surveillance capitalism and the mic subsidized by ignorant customers.
ryan93 · · focus · HN ↗
[dead]
mattbrewsbytes · · focus · HN ↗
Most personal tasks take trivial amounts of time these days. Does a 5th grade teacher or an auto mechanic need a personal assistant? Do we need to be able to book a trip faster? It feels very gimmicky to me, but I realize I'm not their target audience.
Given that, I do think Meta will probably get the lions share of B2C AI and they have a proven track record of using personal data to serve ads and make a lot of profit. If they capture more of their user base's time, it keeps them engaged and away from a list of competitors. If Meta starts crushing it in this fashion I could see IPO's of OpenAI and Anthropic land like fart in church.
rolosa · · focus · HN ↗
It also handled payment splitting. I told it what person x spent for the group split 3 ways (it originally split by the total number of people, but I clarified that only me + x + y are paying) and it kept running totals. When I got an email from Venmo saying x sent me money, muse automatically updated the balance sheet.
We saw some signs written in an unfamiliar language. Muse told me what language it was.
chronogram · · focus · HN ↗
rolosa · · focus · HN ↗
rolosa · · focus · HN ↗
mattbrewsbytes · · focus · HN ↗
Like I said, I'm not the target audience for a personal assistant. That does sound like a more ideal UX than what chat gippity and the others offer though. I would expect that with Meta - they really get the UX mostly right for people.
rolosa · · focus · HN ↗
alex1138 · · focus · HN ↗
But this is where friends are and don't give me 'you could just call them'
Not everyone has access to email/phone. Facebook should work in theory, if they weren't so enthusiastic about intentionally eroding privacy (physically changing the privacy options). Multicast. I post some status to multiple people at once. I can find people I don't already know/have lost touch with, and connect with them
What Meta does, does not mean its users don't care and I wish you people would stop saying that