Not sure why anyone thinks a judges order is worth anything in the USA anymore. I am not reassured at all.

They're not enforced any more. The administration can just ignore it.

If that were the case things would look very different.

Like what would that look like? US citizens being shot in the back of the head by government agents? On a weekly basis?

I mean you just have to look at all of the things that have been blocked by the courts in the last year. Deportations without access to counsel, federalized national guards, a variety of interim appointments...

And before you go there, yes, I am aware the administration has ignored court orders and played dumb afterward. That doesn't mean they've successfully ignored most judicial decisions.

This is definitely Barbara Streisanding right now. I had never heard of OpenCode. But I sure have now! Will have to check it out. Doubt I’ll end up immediately canceling Claude Code Max, but we’ll see.

I don’t know if the Streisand Effect is relevant here since Anthropic will block any other uses of their private APIs, not just OpenCode. The private Claude Code API was never advertised nor sold as a general purpose API for use with any tool.

OpenCode is an interesting tool but if this is your first time hearing of it you should probably be aware of their recent unauthenticated RCE issues and the slow response they’ve had to fixing it: https://news.ycombinator.com/item?id=46581095 They say they’re going to do better in the future but it’s currently on my list of projects to keep isolated until their security situation improves.

Imo I don't trust ANY of these tools to run in non-isolated environments.

All of these tools are either

- created by companies powered by VC money that never face consequences for mishandling your data

- community vibecoded with questionable security practices

These tools also need to have a substantial amount of access to be useful so it is really hard to secure even if you try. Constantly prompting for approval leads to alert fatigue and eventually a mistake leading to exfiltration.

I suggest just stick to LXC or VM. Desktop (including linux) userland security is just bad in general. I try to keep most random code I download for one off tasks to containers.

I'm trying to put together an exe.dev-like self hosted solution using Incus/LXC. Early days but works as a proof of concept:

https://github.com/jgbrwn/shelley-lxc

Incus is great for this use case, I did something similar. I volume mount specific stuff into the guests and let OpenCode loose with all tools enabled.

I used OpenCode to vibe code the shell script I use to manage it.

I actually use VMs rather than LXC, which makes it easier to run e.g. docker.

Very cool. I think docker also runs fine inside of LXC, but haven't experimented too much with that specifically yet.

I might go back and give it a try! It would certainly save some ram.

I immediately reached for VMs because I just didn't want any question about the full level of isolation, but the cool thing about incus is that it should be easy to switch between them.

A coding agent is just a massive RCE, what do you think happens when claude gets prompt injected? Although I don't defend not fixing an RCE.

Absolutely all coding agents should be run in sandboxed containers, 24/7, if you do otherwise, please don't cry when you're pwned.

OpenCode is kind of a security disaster though: https://news.ycombinator.com/item?id=46581095. To be clear, I know all software has bugs, including security bugs. But that wasn't an obscure vulnerability, that was "our entire dev team fundamentally has no fucking clue what they're doing, and our security reporting and triage process is nonexistent". No way am I entrusting production code and secrets to that.

So is Claude. They nuked everyone's claude app a few days ago by pushing a shoddy changelog that crashed the app during init. Team literally doesnt understand how to implement try...catch. The thing clearly was vibe coded into existence.

Last week Claude Code (CC) had a bug that completely broke the Claude Code app because of a change in the CC changelog markdown file.

Claude Code’s creator has also said that CC is 100% AI generated these days.

agreed. This is definitely free PR for OpenCode. I didn't try it myself until I heard the kerfuffle around Anthropic enforcing their ToS. It definitely has a much nicer UX than claude-code, so I might give the GPT subscription a shot sometime, given that it's officially supported w/ 3rd party harnesses, and gpt 5.2 doesn't appear to be that far behind Opus (based on what other people say).

Very cool. Was thinking about working onthis myself after moving in a house 4 months ago with these to all of a sudden ahve to replace them for no good reason.

Exactly. If it is used a certain way by enough people, that is also an accepted definition. Dictionaries lag actual speech and language I suppose.

> If it is used a certain way by enough people, that is also an accepted definition.

This mentality seems to be prevalent in the USA, in Germany, on the opposite, many people see this topic differently - just because a lot of people use a certain word/term wrong does not make it right.

And it annoys me endlessly. People can't let go of the genitive, even if it's dead in loads of dialects.

If people knew how many words were just "made up" in the last couple centuries to match the vocabulary of Latin or French... they'd lose their mind

+1 for cudarc. I've been using it for a couple of years now and has worked great. I'm using it for financial markets backtesting.

Because of public family trees potentially linking a genome to a family, no dna is fully anonymous these days.

The DNA itself is not "anonymous", but I would do it without giving my real name, address, etc. They could know who the DNA is related to, but not gain more information than that.

Even better would be to swap identity with someone else who wants to get sequenced...

They would be able to pinpoint your identity (e.g. "this person is the son of both X and Y, and we know who X and Y are").

And what would that gain them? "X and Y had a son"?

They know who X and Y are, and also know the identity of their son (you), so that gains them your unique DNA sequence, identified as yours specifically.

Yeah, I think you're missing the whole point of the "anonymously" part. :-)

How do you plan to do it anonymously, considering what you now know?:

1. There are already multiple database containing both your parents, you, and a linkage between you and them indicating parentage. So, prior knowledge: Alice and Bob are parents of Charlie.

2. If Charlie's parents have taken a DNA test, there already exists a database linking their DNA to their name. So, prior knowledge: Alice's DNA belongs to Alice, Bob's DNA belongs to Bob.

3. If Charlie takes a DNA test totally anonymously and perfectly untraceably, it will still show up as, child of Alice and Bob's DNA. So, knowledge now includes: Charlie's (anonymous) DNA is the son of Alice and Bob's DNA

4. From these pieces of information, it is trivial to de-anonymize Charlie's DNA, linking it to Charlie's identity: the only person it could belong to is the son of Alice and Bob, and the son of Alice and Bob is already known from point 1.

Ah, I see what you're saying!

I think in my case I'm just not that concerned by the hypothetical because my parents haven't done sequencing/genetic screening and also aren't likely to. I guess the main question is how far out in my family tree I have to think about that. (Also has implications for my descendants, I suppose...)

Clearly not.

Are they going to reinvest these funds into educations so our country can fill these roles or just waste it on weapons and unwinnable wars?

I would be totally fine with this if it was the former, but I would bet that it won't be...

I have not and don’t run an adblocker fwiw.

Just out here raw-dogging the internet...

Try new and improved Bongo Buddy(tm)!

And do you notice high CPU usage or stuttering?

Very cool. I learned a lot as a non dermatologist but someone with a sister who has had melanoma at a very young age.

I went from 50% to 85% very quickly. And that’s because most of them are skin cancer and that was easy to learn.

So my only advice would be to make closer to 50% actually skin cancer.

Although maybe you want to focus on the bad ones and get people to learn those more.

This was way harder than I thought this detection would be. Makes me want to go to a dermatologist.

Thanks, this is a good point - I think a 50:50 balance of cancer versus harmless lesions would be better and will change this in a future version.

Of course in reality the vast majority of skin lesions and moles are harmless and the challenge is identifying those that are not and I think that even a short period of focused training like this can help the average person to identify a concerning lesion.

> So my only advice would be to make closer to 50% actually skin cancer.

If I were to code this for "real training" of a dermatologist, I'd make this closer to "real world" training rate. As a dermatologist, I'll imagine that probably just 1 out of 100 (or something like that) skin lesions that people could imagine are cancerous, actually are so.

With the current dataset, there're just too many cancerous images. This makes it kind of easy to just flag something as "cancerous" and still retain a good "score" - but the point is moot, if as a dermatologist you send _too many_ people without cancer to do further exams, then you're negating the usefulness of what you're doing.

It needs a specific scoring system where each false positive has a lower score drop, but false negative has a huge one. At the same time like you said positives would be much rarer. Should be easy to ask LLM to vibe code that so it would simulate real world and its consequences.

Thought about this some more. I think you want to start at 100% or high so people actually learn what needs to be learned: what malignant skin conditions actually look like.

And then once they have learned you get progressively harder and harder. Basically the closer to 50% you are the harder it will be to have a score higher than chance/50%.

I found the first dozen to be mostly cancer and then the next dozen were mostly non-cancer. (Not sure if it's randomized.) (Also, I'm really bad at identifying cancerous vs non-cancerous skin lesions.)

It is randomized so probably just bad luck! FWIW I get a high score and another skin cancer doctor who commented also gets a high score so it is possible to make the diagnosis in most cases on the basis of these images.