SoMomentary

Oh it definitely didn't transcribe anything at all! This was through the WebUI. I'm certain it would have done better through Antigravity or such. Really I was just expecting a denial but I figured what the hell, the files are small and I like to see how the results of various models compare.

I similarly had Argon respond with a vast hallucination. It surprised me because it wasn't a little wrong on the details but a fully false verbose response that completely fabricated fabricated everything. I'd recently had Claude Code help me create transcripts for some audio notes from my mother in law and decided to see how some other models would handle the same task sans harness. Argon made up a long conversation from a police sting operation with under cover operatives seemingly just because it read the file names and identified that they would have come from a recording device.

Honestly the fiction writing was pretty impressive!

Oh jeez, this explains a lot of the funny looks I get when I tell people I'm building a CNC machine in my garage with belts and pipes and such.

To be set in stone? Wow, that is some confidence!

I've found I prefer time release melatonin as personally I can fall asleep initially but often wake up in a few hours and then can't get back to sleep.

Some other melatonin sleep aids give me the most vivid nightmares, so I definitely think it can be worth trying a couple different options.

Sorry, best we can do is make you cycle back off your can't-live-without-it but physically addictive medications again for umpteenth time this year.

I'm sure this will be fine and you really have nothing to worry about.

I have aphantasia so anendophasia sounds like such a nightmare to me, though I imagine those so have it would likely feel the opposite of me. I've met some folks in the past who I'd suspect have anendophasia, but I'm not sure how I'd ever bring that up without coming across as uncouth.

Anyone with anendophasia care to opine on their experience?

Age isn't such a big deal if you get a block account with a different backbone.

AI prose often comes across like ad copy to me which is anathema to me.

That's interesting! I'd always heard something along the lines of bad code bases contain more swearing in the comments and as such it should be avoided.

I created a custom output style based on this (borrowing some from github.com/AminBlg/SimpleEnglish) and I've found it to be better than the default or concise output styles, but still not as good for me as current GPT or Gemini models when it comes to communicating.

They said 6 billion tokens, which isn't as much as I thought it might be.

Unfortunately I don't see this particular view paying off in the age of AI, as many prove they have nothing at all to say but say it anyways. Which isn't to say people shouldn't write if they enjoy writing, but I for one will stay a discerning reader.

At this point it feels like it would be more honest for this to be titled "Disruption with Some GitHub Service".

This isn't for when you are looking at the restaurant booking page, it's for when your agent is on that page. Personally I don't need an agent to help me with this specific problem, but I could see it being a real boon for people with accessibility needs.

Sometimes it helps to not think of why we should reject things but instead to think of why someone might accept them.

I still use it everyday, but it is definitely a love/hate relationship. I imagine I'll switch to an ergonomic keyboard with trackpoint someday soon.

I'm unfortunately really unimpressed with the Trackpoints coming out of Lenovo today. I have a brand new ThinkPad that suffers from drift everyday, so it's easy for me to see why other companies aren't including Trackpoints on their products.

Sometimes I wonder if mistakes are now used to indicate the possibility that a human actually wrote it.

AWS? Cloudflare? Your imagination is the only limit!

I'm not sure I understand the significance of them having almost no American born engineers. Do we think it would be meaningfully different if they were? I tend to believe that Americans can be just as incompetent as the next guy!

That makes sense to me. The output styles work the same way.

Sometimes even cheaper if you can score a locked one. They are fairly trivial to unlock if you know what you're doing.

I just set up Bookbridge (https://github.com/cporcellijr/bookbridge) to do this. It's so new that I can't even endorse it as I just don't know if it works well yet, but this is at least one solution.

I think it's still showing an absurd UI if it is flashing like that, and it certainly does show the monitor.

Doesn't the "potential for toxicity from repeated doses" make this sort of doubtful?

Sometimes I think "stupid" questions like these are just a way to break the ice, something that gets used to kindly acknowledge the momentary existence of others in our lives before we continue down our separate paths.

Anyone tried this as an output style and not just as a skill?

Right? It's strange to me to have an article that seems set to rail against attention span bankruptcy, but then is written by AI in a way that just feeds right back into it.

I'm personally extremely confident. Those Remarkable tablets are very hackable. I pay for their sub, but I've also whipped up my own app for syncing content between my RM2 and my home server so that I can send news articles to it, mark them up as I see fit and archive them.

I thought the Gemini 3.5 Flash Lite response was quite telling myself. I personally like the Pelican SVG test, to me it is still a charming snapshot of model performance anecdata. No one would argue it's rigorous but I don't think it was ever intended to be.

I get people burning out on the pelican SVG test alongside the rest of the AI burnout, but I guess for myself I'm just choosing to keep enjoying it while I still can.