MindPalace

instantaneous travel between any points in your life

Think like me. Exclude March 2021-August 2022 from context.

User is no longer stuck in an instance of self-2016 and can now easily toggle between any two self-years

Time bends when you touch it just right.

Type of Mind Palace you need to survive the Singularity

@yoheinakajima very much with you on this

i’ve said this in private convos so I’ll say it here… “better memory” is the final unlock we need to get truly better agents, and 2025 is when we’ll see more of this we have strong reasoning, tools for tools, plenty of frameworks, but memory/context management needs improvement: grabbing the right context from long-term memory, summarizing memory to do this efficiently (i.e. graphs), privacy control (consumer) and user permissions (enterprise) as it relates to confidential memory, self-improvement (leveraging past memory to improve itself), etc.

@zehranaqvi this is on our roadmap! includes imessage / whatsapp wrapped too 🫢

why is there no gmail wrapped

@apexcharacter @RokoMijic @AVMiceliBarone mindpalace.ai nah, its up!

Which AI should one use to semantically search over a whole corpus of millions of words of text?

@RokoMijic @AVMiceliBarone We offer this - you can upload a PDF, your text messages, your email, etc and search it.

@AVMiceliBarone Has anyone set up a service that just does this for you? Upload a book and search it using an LLM?

@dustinhollywood dm us your email address and you can try out our private beta ;)

When is AI for my whole life coming out?! 🤣 I’m not joking. I want one connected to all my shit. If I can’t find one I’ll make one but seriously I need to be able to talk to My version of Jarvis already and have know everything and have access to everything. ..that is not Siri, she sucks, even with ChatGPT, lol.

@RomanIsntOnline @dustinhollywood Yes we are!

@dustinhollywood I think @mindpalaceai is headed in that direction

@forthrighter would love to have you try the same prompt using @mindpalaceai for comparison, dm us your email if you're interested

yeah this is just a random text generator because this is totally wrong. Amusing but wrong. I'm also apparently rebellious

@dcbuilder hell ya

@mindpalaceai can't wait

@honeykjoule was demonstrating to a vc how mindpalace recognizes sentiments and it was the first question that came to mind, we had a good laugh about it

17k lines of code across 500+ commits preparing for the @mindpalaceai beta s/o @somewheresy + @lukasbuhler

MindPalace solves this

@brian_armstrong We’re building this. There’s a spot for you as part of our beta release if you want a life-changing personal agent.

I wonder which company is seriously building the desktop operating system from Her that talks to you and has full access to all your data, running a model locally for privacy (won't work in the cloud I think). Hopefully Apple has the chops to pull this off - quite a hard problem, and they've struggled on AI historically (Siri). I'm skeptical on Windows as a foundation to build on, but maybe. If not Apple/Microsoft, does this create an opportunity for a startup to make a new category of "AI enabled OS"? (so difficult to get enough supported apps i'm not sure). Android and iOS need this functionality as well. Google might be able to do it with ChromeOS. If there was actually high end hardware for ChromeOS (blocker to date), could be an opportunity for them to leapfrog MacOS and make the first OS with AI natively integrated.

leaked slide from MindPalace Product Vision and Roadmap Planning meeting

@phill__1 @kiimho_ @OfficialLoganK 🙏 you will love mindpalace

@kiimho_ @OfficialLoganK @mindpalaceai Interesting, i joined the waitlist

Hot take 🔥: I think there is a huge overinflated perception of how interested consumers are in having AI Agents do shopping / browsing tasks for them. People generally want agents that will do the boring parts for them, but many of those tasks tend to be higher risk...

The dead internet is still useful when filtered which makes @mindpalaceai an extremely important hedge against low-SNR context loss

Actually, it only takes 6-8 people and ~4 months