D13Fd

I actually don't mind it. They did the work of generating the font files from the public domain works, and you're paying them for that work.

A big part of the problem, in my view, is that the process of creating the art/graphic design/writing was to think and be creative. Having to do the work itself led to a wide variety of outputs that were interesting. Now that's often gone.

And if the work is an ad, a flyer, etc., the quality of the output used to signal something about the event or product. Not so much any more.

There is nothing to be done about it, but it's still a real tradeoff.

The problem is not that people aren't doing work, it's that everything starts to look and feel the same.

With code, that doesn't matter so much. We are using it to achieve real-world objectives. The creativity of the programmer is rarely at issue -- from the user's perspective, a programmer is more akin to a plumber or an electrician. What matters is the result, not the creativity of the code.

But it does matter when part of the point of an in-person event is to see and appreciate someone else's creativity and skill. There is a real difference when that creativity and artisanship is replaced with AI output.

If I want to see AI art, I can prompt a model all day long and see whatever art I want, customized to my preferences. It's freely available and easy to get, so it doesn't have a lot of value.

I have to disagree here. I don't have a bias against AI art, but I've noticed some real effects with public events:

1. You can no longer judge what an event will be like by its materials

2. Everything starts to look the same, and you feel like you've seen it all before

Maybe these effect will attenuate as people start getting more adept with AI. But I think we're in for a least a few years of this.

It felt wrong to me when they split iOS in two to make the iPad OS, and now it feels super wrong.

The whole selling point of this is that it’s an iPad mini in your pocket, IMO. It’s really a shame they couldn’t give it all of the iPad’s best features.

Just grade it like law school (in the US). Homework means nothing, and only the final exam counts. The final exam is administered in a room where you have no access to AI.

So much this. I’m using these models primarily for dumb hobby projects and I’ve still hit this a lot - although much less so in Opus 5.5.

That's what I'm finding too. Opus 5.5 feels both consistently better than Fable and faster.

I just hope they sell off the IP rather than letting it stagnate further. There are other game studios out there who could do a lot with it.

Honestly I bet Obsidian is next, and I'm not sure I'll mind. I still love them for the great games they've made in the past, and still I buy their new releases, but they haven't been able to pull off a compelling game since Pillars of Eternity 2. That was 8 years ago.

Copyright is grossly overbroad. Corporations should not get to own our collective culture for life of the author + 70 years. It's insane. It's hard to feel pity for them.

The aggressive moderation on StackOverflow was so annoying. I still remember multiple times where I found a question about my exact issue, but it had been closed as a duplicate, and the "duplicate" was basically irrelevant.

There are a few different types of Markdown apps. Many of them work like Notational Velocity/nvAlt/Obsidian where it's a folder of plain text files, you type in Markdown primarily, and the editor just applies some formatting after the fact, akin to syntax highlighting. IMO its much nicer than looking at just the Markdown, but it also has the advantage of remaining 100% portable text.

I’m running 27B on a 5090 as well, and the results have been really strong. It does almost as well as, and sometimes better than, a 121gb DS4 model running on an M5 Max 128gb. 27B also flies on the 5090, and at medium think it returns results many times faster than my DS4 setup (the default xhigh is basically broken, though).

For the kinds of things I use a local model for (legal document review), it’s just spectacular. It also has good vision support. I’ve been using 27B more and more over DS4.

Why would an issue in the SpaceX data centers impact Claude / Anthropic? Work shifting over from Grok->Claude?

The example is particularly bad because in Skyrim the blacksmith actually does react when a dragon arrives (in one of the villages where the blacksmith is on an exterior cell) and can actually be hurt by the dragon.

I got what they meant by "OS" about 10 seconds after landing on the page, but I still think it's a bad term here. The system is not controlling the operation of the home or of the people within it. It's a home-centric to do and calendaring app.

I’m fine with Firefox and run it as my main browser on all my devices. But their corporate behavior means I’ll never give them my money again.

Excellent analogy. This paragraph invalidates the entire post and honestly just looks lazy. The author may be right anyway, but with that level of experience with these tools, he is really just guessing.

I’ve been running DeepSeek 4 Flash, Qwen 27B and Qwen 9B on local hardware. They work well for coding and document review tasks. I think Qwen 9B local on a 5090 might be legitimately helpful for small task agents in omp, since it is ridiculously fast. But my motivation is that I have data that I unfortunately can’t share with 3rd parties.

I have been eyeing a 512 GB Mac 5 Ultra to run full DS4 pro locally, which I expect would be pretty amazing as far as quality/recall. The only downside is that the speed is a lot slower than something like 27B on the 5090.

Because I felt the opposite a while back when I switch from OpenAI->Anthropic, and because I understood that the two companies were basically at parity right now on their frontier models.

Yeah but Sol shows it is possible to just send the readable explanation in the first instance. And I don't want to spend tokens and time on asking for a better version of each response.

Fable is much better than Opus 5 IMO but it just burns through tokens ungodly fast. I can hit my weekly Fable limit on a 20x Max account in a day.

I think you’re right. It’s not optimized for some kinds of work. My little project has a Textual TUI interface that needs to display a few hundred thousand rows in a table. It takes 14 seconds to load in the default datatable component. I instructed Opus 5 to replace the datatable component with a fasttable alternative, a new dependency. I let it go overnight.

When I got back up, it had spun for hours and proudly announced that, instead of doing that, it had optimized the datatable build and avoided the dependency, because the new datatable loaded in 11 seconds. Once I got it to actually make the fasttable version, it loaded in less than a second…

I’ve been doing some heavy work on a personal project lately. I burned through the limits on Claude, the plus a few hundred dollars in credits, and ultimately decided to move to an OpenAI account just so I can keep going.

I was surprised to find that OpenAI Sol is much much nicer to work with than Opus 5 or Fable at the moment. Especially on Opus 5, the way it communicates is just exhausting. It keeps “being honest” and “confessing” mistakes and just generally talking a lot. I felt like I had to really dig to see what it’s doing.

The project involves OCR, and despite repeated instructions not to, both Claude models keep spinning out a bunch of agents to re-invent the OCR setup, and they inevitably seem to invent a primitive serial version that takes 20x the time, or longer, to complete, and then running it against thousands of docs. Basically I have to watch it like a hawk or it just spins out on red-teaming tasks that take hours and hours.

I don’t know what its system prompt is, but Sol/Codex is just so much nicer to talk to. It only asks exactly what’s needed, it tells me only what I need to know, and it is just generally workmanlike. And it has not once decided to spawn an agent that spends hours pointlessly burning tokens and CPU cycles re-inventing the OCR process. I’m really liking it.

Is it, though? It was highly effective with basically zero downsides, and well executed. I’m honestly not sure what the problem is.

I have a keyboard I bought in 2020 called the Makerdiary M60 keyboard. It runs Python, and over the years I've coded in various functions. But it was somewhat buggy, and the upstream firmware was never upgraded.

I love the hardware because it's the only keyboard I've been able to find that keeps a live Bluetooth connection and lets you toggle back and forth between USB and Bluetooth instantly using only a keyboard shortcut. That means you use two computers, and switch back and forth as fast as you can type. Years ago I also added a feature that changes the backlight color based on the active connection, so you can instantly tell which computer your typing will go to. I haven't been able to find any other keyboard that's quite as nice.

Lately I've spent weeks using an LLM to update the extremely old keyboard firmware to the latest firmware of its components (e.g., Circuitpython, the BLE firmware, the boot loader) and implementing all of my dream keyboard features that I never had the gumption to spend hours implementing pre-LLM. I finally resolved years-old bugs, and I added things like layer-based backlighting (so that the individual keys with relevant functions are lit), a better battery gauge, better sleep/suspend timing, backlight calibration, better debounce, and so on.

I've also upgraded the hardware and added batteries to each of the keyboards (I have three of these, one at home, one in the office, and one for travel).

It has been a very satisfying project, finally scratching a years-old itch.

Exactly. And having AI to work out the 2am dependency issues actually makes maintenance a lot easier. This seems like an odd message.

I agree. I assumed an optimal path would leave the mower on the outside of the property, to easily return to storage. But the “optimal” solutions in the article leave the mower wedged between three rocks. That seems rather sub-optimal to me.

I’ve been using this for weeks, and it’s pretty incredible. I used to get motion sick especially quickly when I looked at my phone in a moving car. Now it’s the opposite, if I’m sick in a moving car, I try to look at my phone, which magically fixes it.

It’s amazing how that sick feeling in your stomach can be fixed by looking at some purely visual moving dots.

There is zero reason to shred 18th century books. Any such books are out of copyright.