Viewing profile — sReinwald

Framing this as whether he can convince you the mistype was accidental gets it backwards, and "would I believe X or would I think Y" is preponderance, not reasonable doubt - entire…

I'm from a region bordering the palatinate region and I'll absolutely back you up on being able to understand them pretty well. There's an amish guy who sometimes pops up on my Tik…

> at a breakneck pace for no apparent reason, lately. This isn't surprising to me at all. The World Cup is on, and it draws attention away from politics. This has been a pretty com…

You clearly haven't played WoW in a decade, judging from this comment. > Even if you buy the expansion just to get the "feel" on how it was, it's impossible. You don't buy previous…

Yeah, totally valid for things like D&D - I split that out too, for the same reason. Work and homelab overlap constantly for me though. I make heavy use of periodic notes, so even …

I keep one vault for almost everything because the cross-domain links are where the interesting stuff happens. I studied sociology, political science, and media & communication bef…

Third-party MCP servers create at least two different security problems. One is prompt/context injection through the tool output. The other is the much more conventional risk of ex…

"It's not a complaint about water. It's a complaint about the wetness." If capitalism requires constant vigilant government intervention to prevent monopolistic practices, anti-com…

Any single LLM-edited comment reads fine in isolation. The uncanny valley kicks in when you read thirty of them in a row and they all use the same "it's not X, it's Y" construction…

> Overall this was a worthwhile assist. I believe (totally understandable) anti-AI animus is coloring a lot of these replies. That, and hindsight bias. People know the second versi…

Interestingly, when I apply the "simply repeat the prompt" technique [1], Sonnet 4.6 on the website got it right every time, both with and without extended thinking. Not repeating …

You are essentially amortizing a single dose over 6 months by micro-dosing and receiving a clearly sub-therapeutic dose. While that may work for your specific usage, it doesn't cha…

I suspect a big reason for why Mounjaro is still fairly expensive here in Germany (I pay nearly €400 for a 10mg Qwickpen - a 12.5mg Qwickpen is nearly €500) is due to health insura…

It would probably be interesting, but if you are not overweight, the appetite suppression will likely make this not a very healthy or very fun experiment. I started at 5mg in Octob…

One thing I have noticed on Mounjaro is a (at least subjectively) significant decrease in impulse spending / buying random crap off Amazon. I have ADHD and that has been a real pro…

Like I said, the first examples are fairly trivial, and you absolutely don't need an LLM for those. A good agent architecture lets the LLM orchestrate but the actual API calls are …

> But can't you do the same just using appropriate MCP servers with any of the LLM providers? Yeah, absolutely. And that was going to be my approach for a personal AI assistant sid…

You could, but Claude Code's memory system works well for specialized tasks like coding - not so much for a general-purpose assistant. It stores everything in flat markdown files, …

Disclaimer: Haven't used any of these (was going to try OpenClaw but found too many issues). I think the biggest value-add is agency. Chat interfaces like Claude/ChatGPT are reacti…

Not saying the frontier models aren't smarter than the ones I can run on my two 4090s (they absolutely are) but I feel like you're exaggerating the security implications a bit. We'…

IMO the value and differentiating factor is basically just the ability to organize them cleanly with accompanying scripts and references, which are only loaded on demand. But a ski…

I don't see how that makes it uniquely viable in France. Germany has something very much like this too. And we've had it for nearly 13 years. > Since 31 August 2013 companies which…

It's been a few days, but when I tried it, it just completely bricked itself because it tried to install a plugin (matrix) even though that was already installed. That wasn't some …

From my experience: TDD helps here - write (or have AI write) tests first, review them as the spec, then let it implement. But when I use Claude code, I also supervise it somewhat …

[dead]