I started using Zed a couple weeks ago and immediately had issues with copy/paste/buffer on an M1 Mac. I tried a few suggested fixes and they didn't work.
I live in Las Vegas and one year at the start of summer my AC went out. It took a week to order the part needed and make the fix. I lived out of casinos for that week (using HotelTonight to get a different place each night) and it was pretty fun. I gained 10lbs. That said, AC's are a necessity out here.
I live a few hours outside Las Vegas and it's a lot more survivable than you would think given primitive technology and some knowledge.
I have one of those portable evaporative coolers and they don't need much power (50-100W). I have one and measured ~110F input and 78F on the output side using nothing more than water and a fan, pretty remarkable. The trick is staying out of direct sunlight, and the body can cool itself well with the same mechanism. Sweating is extremely effective due to the low humidity.
Absolutely. In the northeast US we have triple redundancy on heat, because it’s potentially life-threatening to have the heat go out in a blizzard with subzero temps. I’d treat cooling redundancy as similarly important in Nevada, especially if not very mobile.
I think it's far from dead-on-arrival. I don't want to buy a PC, put it in a garage, etc. I want a little box I can easily hook up to my TV and play Steam games on. This scratches that itch. I'm old and want convenience. I know a lot of other people in my peer group who are going to pick one up too. Also I don't play any competitive games where I care about anti-cheat. I just want to play my RPG/JRPG's on a big screen and I want it to be plug-n-play.
I think dead on arrival is too extreme but the niche is certainly hard to see. The "just works" crowd will buy consoles and the "max performance" crowd won't be happy with this value. The niche is something like "willing to tolerate some headaches but not so much as to build my own PC". That exists but seems small.
Feels like they should have gone cheap. Undercut the switch and be the cheapest way to play games on your TV. We're pretty far past performance equalling more entertainment. A 150-200 box to play indie side scrollers is a niche that exists.
I don't buy consoles because I have been a PC gamer for over a decaded. But you know, I'm a parent now. And I want couch gaming with my family. That's the use case for me my family. I got mu child a steam deck (I have one too). A steam deck is a terrible idea for an elementary schooler. It has to stay docked now because she's already broken parts of it.
But even docked, it's a winner for her and all her friends. She's converting more parents over via her friends. The well off ones are just buying from Valve like me. The less so, are using whatever PC is around to mixed results. I'll see how it goes as the kids get older, but I think there's a bigger case than you think and I think it's mostly years long PC gamers who want a more communal experience be it with partners, kids, or friends.
The reason I'm going to buy a Steam Machine instead of building a computer is the verified program.
I've absolutely loved being able to check a store listing page and immediately know if a game will run well on the Steam Deck. Having the same program for a higher end target would be really nice for me.
Also, getting the CEC right is really valuable for me. If I'm building a computer there's no chance I am going to be able to get it to play nice with the TV using just the controller.
This runs SteamOS and is an officially supported platform that, if it has legs, will be something developers may want to target as a platform and make sure their games work a la Steam Deck verification.
There's also potential for community fixes for older games with issues. And easier troubleshooting cause you can just look up "fix for X game Steam Machine", or "does X game work on Steam Machine"
There are advantages to this over something generic, or building your own machine.
Yeah I understand I can get a much better gaming PC at much lower price point but that was kind of the point I was trying to make. I'm in a position where I'd happily pay more for convenience and I know many other people who feel the same way. I think there is a huge market here and this isn't a dead-on-arrival situation at all. Valve knows this.
Yeah, for sure people will buy this for those reasons. Some people also bought an nvidia shield and other gimped android boxes. It's honestly really disappointing though. I would love a steam machine to be competitive and cost less and eventually phase out windows gaming. This hardware launch falls really short though. The appeal is going to be limited. Oh well, maybe next time.
I don't think that market is as big as you think it is and if anything, it's only going to push people away from the Steam Machine into another micro PC platform that will be able to run Steam OS.
There's also the kid factor if you're playing on the TV in the living room. Kids have a way of walking in at the worst time. As someone who enjoys violent titles, I get it.
This line should be auto-pinned at the top of every single HN thread where the topic crosses over into target markets for products. (I'm joking, but the point stands - HN is both wildly different than the average individual and many of those on HN overlook that fact)
I just bought a WalkingPad M2 and my first day on it was yesterday. I usually sit on my couch while working. I walked about 6 miles yesterday instead! I woke up with sore calves and I think I'm getting blisters but these are probably good signs.
Hah! I was too. I was at a bar with Chris trying to convince him to base the company off of hg instead of git but they already had the domain name and had already started building it.
> Claude basically disregards your instructions (CLAUDE.md) entirely
Does anyone know of a way to fix this? Claude constantly disregards my CLAUDE.md. I put a decent amount of time into it and it's pretty much worthless without explicitly telling it to reference it before each prompt.
I've found really hammering it with *important*, all caps, "NEVER", etc finally made it start using the tidewave MCP for elixir development well. It felt really heavy handed but it worked.
To solve it, you just don't allow your current context to use more than 50% of the total window size
To do that in Claude code, you have to use subagents and design small enough agents
Then you can use skills to make it remember every time the little details or the steps
More effectively, you use skills to tell the main thread when you go to use which agent.
If you don't understand anything I said, try to restate the important things to the model periodically, and keep your tasks small.
Use plan mode and make the model store, keep track of the progress on a markdown file, and when context is polluted, call /compact and then make it re-read the context from the files created
You can prompt it as simply as:
First, understand the login feature on the repo using subagents and create a document on docs/ for future reference. Then, understand the task at hand and create an implementation plan.
<task>
blah blah
</task>
Also, using XML tags makes the attention remember easily
It's better if you think that the only thing that is really there is a context window.
They can add complex concepts and tools on top, but all that is is a different way to put things in the context window. Even the chat history on the web... You are not sending a message every time... It's not really a chat... the model is writing what it predicts will come next, like autocompleting a Word document that is written in a chat-like format.
So agents are like you, opening a new window and having the chat there, so you don't pollute the current window with all the tokens needed to process that question, and to use only the output here.
This is important bc of the effective context window problem. Models are more accurate the smaller the context is.
Hence, MCP tools are problematic. If you have registered many of them, the rules for using each one are added to your context, even if you don't use them.
Having a very extensive Claude.md file is also problematic.
You can use skills to instruct the model on which agents to use when requesting a specific thing. Antrophic says they have trained the model to discover on its own when to read the skill and follow the instructions you picture there, which can include Python scripts to run.
So yeah, agents help the model save context window for your current problem, skills help the model follow your instructions better, and instructions can include agent calling, and MCP is crap, you'd better ask the model to generate code to make that call
Oh, there are also slash commands. I don't really use them... if someone has a success story for them, I would love to know about it.
Skills are just reusable prompts in a convenient package.
Subagents get their own pristine context window to go off and perform some task. They can also run skills and do lots of context-heavy work and report back some small sliver of it to the main agent as a report.
Skills are more than just reusable prompts, since they can be packaged alongside with runnable Python or Node scripts that the model can use to achieve what it needs.
