dwood_dev

Not for enterprise users, they pay per token, even on chatgpt.com.

CPU is a rather weak Zen2. If that still appeals to you, instead purchase a BC-250 mining board. It's a PS5 reject and nearly all of them can be fully unlocked for all 40CUs and 8 CPU cores. They are quite popular right now for building Steam Machines and all the hacking has been done with replacement BIOS mods.

The clock is ticking even for that. We're not far off from anything being able to be copied, including streaming only games. If it can be observed, a reasonable facsimile can be created. The reasonableness will increase over time.

Given the similarities in port layout (just missing a HDMI and USB3 header), and that the case is nearly identical, I would guess that this router probably is a custom run of the exact same BananaPi board without those headers. Both also use MiniPCIe in 2026, which is a bit of an odd decision.

Might be a difference in use cases. Mostly working in repos under 100k LOC, most of those are under 30k. Primarily golang, python, and terraform. Also a lot of interactive troubleshooting of Kubernetes, GHA, hardware debugging and application debugging.

I also only run in fast mode on gpt-5.4 high.

I use both. I avoided codex in late 2025 because it was slow as molasses. I tried it again in February and it was on par with Opus speed.

I like codex(gpt-5.4 high) more for its ability to nitpick my PRs and find bugs. I like opus 4.6 much better for anything dealing with visuals, but I feel its rule adherence is inferior and it is not nearly as thorough on code reviews.

I like working and building better with claude, I like fixing bugs better with codex. Also, claude is much better and faster evolving with skills, plugins, new features I find useful, etc. Codex is always a month behind or more.

I did both for a month at higher tiers, $200 Claude Max and $200 ChatGPT Pro. I was always having to conserve my usage with claude, with codex I could just let it run wild with no cares. In the end, I downgraded claude to the $20 plan and use it on occasion, and I have kept the $200 codex sub.

I also have Claude at work, so I'll know pretty soon if I want to swap subs again, but for now, I'm sticking with codex at home.

I'm looking at a new car later this year. The limited options for V2H are disappointing.

This predates AI. I've been interviewing candidates(SRE/DevOps) since 2018, so many candidates that claim to have extensive experience with things completely fall apart when you put them in front of a terminal.

No, it happens even with AirPods Pro/Pro2.

I have two iPhones and a MBP. I have to keep Bluetooth disabled on the MacBook otherwise it randomly triggers while I'm between podcasts or whatever and squeeze the AirPods to resume, instead it launches Apple Music, or some browser tab starts playing audio.

This is far from solved if you have more than one Apple device.

There is no option for me to say: never use AirPods for anything but podcasts, and absolutely never automatically select them as an audio source for zoom/teams. AirPods microphones just don't work for my vocal range, they sound horrible and underwater. The microphone on my MBP works great, the mic on my iPhones works great.

AirPods are fine if you only ever use one device at a time. If you use more than one at the same time, it becomes extremely annoying.

Let's not even get into the annoying ways which it becomes hard to manage when you have multiple AirPods, multiple iPhones, and multiple MacBooks.

There is a weak association with use of PPIs and memory loss. I myself noticed a difference once I stopped taking omeprazole regularly.

ubnt has been the ubiquiti default login at least back to 2010 when I started using their products, before UniFi was a brand. I always assumed it was short for Ubiquiti Networks.

I had a bash spaghetti code script that I wrote a few years ago to handle TLS certificates(generate CSRs, bundle up trust chains, match keys to certs, etc). It was fragile, slow, extremely dependent on specific versions of OpenSSL, etc.

I used Claude to rewrite it in golang and extend its features. Now I have tests, automatic AIA chain walking, support for all the DER and JKS formats, and it’s fast. My bash script could spend a few minutes churning through a folder with certs and keys, my golang version does a few thousand in a second.

So I basically built a limited version of OpenSSL with better ergonomics and a lot of magic under the hood because you don’t have to specify input formats at all. I wasn’t constrained by things like backwards compatibility and interface stability, which let me make something much nicer to use.

I even was able to build a wasm version so it can run in the browser. All this from someone that is not a great coder. Don’t worry, I’m explicitly not rolling my own crypto.

It seems to me like it would be a rather useful exercise to have the smaller model make the routing decision, and below certain confidence thresholds, it sends it to a larger model anyways. Then have the larger model evaluate that choice and perhaps refine instructions.

I really would like to see a cost and cooling breakdown. I just can't see how you can do radiative cooling on the scales required, not to mention hardening.

I thought this was a troll by Elon, now I'm leaning towards not. I don't see how whatever you build being dramatically faster and cheaper to do on land, even 100% grid independent with solar and battery. Even if the launch cost was just fuel, everything else that goes into putting data centers in space dwarfs the cost of 4x solar plus battery.