HN user

MrDrMcCoy

858 karma
Posts2
Comments594
View on HN

In the same way that I'm uncomfortable with Opera since it went Chinese and Chrome from all its corporate spyware, I'll be skipping over the Russian stuff.

Depends on the platform, I expect. I love the feature set and layout, but it's been unusable for me as a daily driver on Linux from various bugs. I'll be giving it another honest go when it's out of beta.

As someone that does, I disagree. Laws on this subject should exclusively apply to providers, with exceptions for medical necessity. There are too many harms that come from targeting individuals to be worthwhile.

Llama.cpp should be rolling out support for this soon if they haven't already. Cactus is a but more targeted for efficient ARM execution, but I haven't been keeping up with what all they support. Would be worth a feature request if they aren't working on it yet.

I miss codeine cough syrup. It's the only thing that's ever been effective for me, despite my being fully immune to the "fun" aspects of opiates. They do remove pain, coughing, etc, but do not add any sensations or impair normal ones in my case. I've tried most of the gamut in one medical setting or another.

There should be a class of drug where the pharmacist gets to decide, based on some registry, whether you get to have something.

Always excited to see new things like Hister in the search space. What are the scaling limits, as far as you can tell in terms of how much can it hold before queries start breaking down or become too slow to be useful? Could it evolve into a general internet search engine if, say, enough trusted members of a geo-distributed YugabyteDB cluster and an army of crawlers built a sufficient index?

It's a good model for sure, but it's training set is based on some pretty old stuff. Would be good to post-train any languages / frameworks you care about being current into a LoRA for it. I even had to do that for the newer Qwen3.6, but it wasn't too hard thanks to Unsloth.

I'm a neophyte. What makes a harness special or all that unique from another? I've had a reasonable experience with Zed and local models, but could be persuaded to put something else in the mix if there is a measurable benefit to be had.

Everyone should distrust them equally. Only local agents in a detached network namespace are safe from data leaks. It is perfectly reasonable to assume they are using our sessions to train on, since everything else short of nuclear launch codes is already there, and they need to keep feeding it.