I generally run chrome/firefox and vscode full screen, and then alt-tab between those and my email (outlook at current company) and messaging (slack). Plus terminal window/s. That workflow is mostly reproducible across win/mac/linux. What features are you using that MacOS is getting in the way?
Decent package manager, brew is awful compared to apt. Window snapping can only be done on Apple keyboards not on external keyboards. No Alt+Tab, Cmd+Tab is not the same. No window previews when hovering over dock, ridiculous animation speed when switching workspaces that can't be changed (and somehow Ctrl+1/2/3 is 2x faster than Ctrl+Left/Right? What is that all about). Needing third-party apps for basic things like: setting a custom resolution (BetterDisplay), setting scroll direction for mouse wheel independent of touchpad scroll direction. And the Settings app is super slow.
What is bad about brew?
I have used it in the past and I found it fine. With apt I have less experience since I only used it when playing with a raspberry pi.
I find it generally slow and by default it gets in the way in a very annoying way.
Without disabling the feature l, every single time I try to install something it also looks for updates so instead of installing a single package I end up upgrading many additional packages
USB-C PD (power delivery) has been a standard for over a decade now. I first used it on a Nexus 4 or 5, and later on a Chromebook Pixel in 2016. It would be surprising for apple to not use that standard, particularly when both ports are probably run from the same controller.
Can someone reccomend to me: a service that will generate a loopable engine drone for a "WWII Plane Japan Kawasaki Ki-61"? It doesn't have to be perfect, just convincing in a hollywood blockbuster context, and not just a warmed over clone of a Merlin engine sound. Turns out Suno will make whatever background music I need, but I want a "unique sound effect on demand" service. I'm not convinced voice AI stuff is sustainable
With the prompt "WWII Plane Japan Kawasaki Ki-61 flying by, propeller airplane" and setting looping on and 30 sec duration manually instead of auto (the duration predictor fails pretty bad at this prompt, you need to be logged in to set duration manually) it works pretty well. No idea if it's close to that specific airplane though it sounds like a ww2 plane to me though.
Everyone is going to have their own flavor of Open Claw within 18 months. The memory architecture (and the general concept of the multi-tiered system) is open source. There's no moat to this kind of thing. But OpenAI is happy to trade his star power for money. And he might build something cool with suddenly unlimited resources. I don't blame the guy. OpenAI is going to change hands 2-3 times over the next 5 years but at the end of the day he will still have the money and equity OpenAI gave him. And his cool project will continue on.
The big draw of open claw is the memory architecture. Because you effectively start from scratch every time you open a new claude chat. Open Claw on the other hand, it compacts regularly, but also generates daily digests, and uses vector search, and then uses thoughtful memory retrieval techniques to add relevant context to your queries. Recent things get weighted more heavily, but full text search of all chats is still possible, and this is all managed automatically. Plus it uses markdown so the barrier to entry for manually auditing/modifying memories etc is very very low. If you say "can you check if my solar panel for my power generator arrive yet?" it is going to probably know what I'm talking about and go check my email for delivery notifications, based on conversations I've had with it about buying, ordering the solar panel etc. Claude is just going to ask clarifying questions since it has no idea what I am referencing.
So it sounds like you get extra memory at the expense of having to compact more because, of course all those things are going to take up context. But since you’re not interacting with it in some kind of turn based fashion it makes it worth it— the lack of context doesn’t matter. Is that correct?
Yeah it's basically just a smart compaction and retrieval algorithm, blended with vector search of uncompacted memories. The algorithm is open source, but the technology behind securing the agent against 1-shot prompt injection will not be.
I can just look at my front porch to see if there's a solar panel there, or failing that I can click a single button on my phone and search "solar" on my gmail and find out where my solar panel is. Having an agent do that for me saves me like... 5 seconds?
Sure. I am (literally) currently feeding a newborn, my house is a diaster zone, and it's raining. DHL just changed my delivery date from today, to the 19th so maybe it will arrive today, maybe it won't. I haven't slept more than 4 hours in 3 days so getting an answer via voice memo seems pretty nice right now.
Slack would be a lot better if they supported clients via rest api or similar. I want to run it in a terminal window alongside IRC etc. I have no desire to put up with their ridiculous UI/UX decisions
If self driving cars replace humans, I can safely bike on the road again, not having to worry about some exhausted soccer-parent scrolling tiktok on their phone in their minivan as they use me as a speed bump. Also as a parent/part time family taxi driver, I wouldlove to get back the ~10 hours a week I spend staring at the road. Kids will be driven by waymo to Karate, Soccer, Violin lessons etc. I am ready for this future.
I usually talk with the agent back and forth for 15 min, explicitly ask, "what corner cases do we need to consider, what blind spots do I have?" And then when I feel like I've brain vomited everything + send some non-sensitive copy and paste and ask it for a CLAUDE/AGENTS.md and that's sufficient to one-shot 98% of cases
Startups might thrive there, but business investment in England (particularly in mature businesses) has not exactly been lively ever since Brexit. I can't recall the last time I heard someone talking favorably about investing in England, or at all, really.
reply