resonious

"This is the part where you think/learn" and "this is the part where you just let the LLM figure it out" is a fine format for advice nowadays I think.

I am getting a little tired of every single HN comment being about how the linked article is written by an LLM.

This seems like a lot. I told my oh-my-pi agent to build my ios app for me and send it to me remotely. After some chugging, it gave me a tailscale funnel link. And it worked. I didn't have to dig into any of this stuff. I didn't use the words "Developer ID-sign", "notarize", or "staple" in my prompt.

I think the moralities of all the big heads in AI are questionable. The training corpus is largely stolen, and they are all in inescapable debt but keep going. But at this point, their products are so useful that almost nobody is willing to sit back and wait for a "morally acceptable" LLM to come around (which would inevitably be inferior).

I can't comment on CSAM though - if X.ai really is "okay" with it then I'll agree with you that they're more immoral than the others.

~13 yoe, and I had some nasty WebRTC + CallKit problems that Opus couldn't make a dent on but Fable figured out.

This is an old rumor but I thought Nintendo made a loss on the devices. If that's true, why would they want to sell more?

Okay I hadn't heard of Vending-Bench until reading this and it was quite the ride learning about it through this article. Very fun read.

My very native programmer take is that it's not too surprising that their hacker model would be less ethical. The guardrails that separate Fable and Mythos probably wouldn't kick in during an environment like this.

Over optimizing and spending too much time on engineering decisions is also something an incompetent development team would do.

I think it's the tiny chance they it will help humans that makes it so fascinating.

Look, I felt it. I didn't wait for the official apology from Anthropic. I quite before they published that, then felt very vindicated when they did.

Deja Vu... This looks just like the Claude Code performance regression back in April. I just quit my Claude subscription when that happened and went to Codex.

Now I'm kinda thinking of trying per token for both, using GLM 5.2 on Fireworks for most tasks, shelling out to the big boys only when needed. Not totally confident I'll break even though.

Claude Code downgrades loudly but I'm not sure what happens over API or with other harnesses, OpenRouter, etc.

Yes you pay a big burst right after switching. After that, everything is cached and it's smooth sailing.

I have clients waiting for very gigantic features and the agent harnesses are a godsend.

This lines up with my experience with my mother, though it played out differently. In her case, she would switch doctors every ~5-10 years and each time they'd basically say everything the previous doctor said was wrong. First it was "you have Lupus", second it was "actually it's some other autoimmune disease", then it was "actually whatever you had has been in remission for some time now and you've been taking brain-numming medicine for no reason." Then it was "you have cancer", "it's a rare one", and "oh turns out the brain-numming meds have a correlation with rare cancers". The cancer part was handled well (albeit unsuccessful) though. After such a bad time with rheumatologists, I was shocked by how competent people were when it came to cancer.

All of the above was intertwined with brief stints with doctors that would just berate her for being a painkiller junkie, even though she hated the stuff and just wanted to find/fix the problem.

Kind of a rant, really. I'm not sure how to tie it back into AI. I do wish we had AI at the time so that we could at least cross-check, but I also understand that doctors are already sick of patients self-diagnosing on the web and that AI probably just makes that worse. At the same time, if our medical system could catch up a bit (more doctors? less corruption/paperwork? not sure what it needs) then maybe people would be less inclined to take matters into their own hands.

I live in Japan and yet can't seem to pay for their API in JPY... I bet their enterprise customers don't have that problem but it was pretty annoying given "AI in Japan" appears to be there only selling point.

It means scores well in common benchmarks.

This is interesting. Though it doesn't seem like it'd translate well to a physical keyboard, leaving me with two different layouts to work with.

Maybe I'm mistaken though. Are there any physical clearflow keyboards? Are they any good, or does clearflow really only work well with swipe?

At this point the only OS with a consistent look and feel at all is Mac. For the other OSes, I don't even know what a "native" look and feel would be. And most apps have their own branding and style they want to tout anyway. So I don't think "apps should look native" is the leading reason to not use Electron.

For me, the leading reason to use Electron is the fact that I already have a browser running so why not just use that to render your webpage... Make it a PWA if you want it in its own window.

Yes this is the thing with these new tools. You have to know when to use them and when not to.

Good ol' software architecture tricks can also help you slot "vibe coded" components into a larger system safely.

All Claude models are huge suck ups. The "you're absolutely right" meme is real even if that exact phrase doesn't show up as much anymore.

I don't want to start a fight or anything but IME Codex has a bit more of a spine. If you point out something weird, it sometimes gives a good reason for it. Whereas Claude will always say "whoopsie you're right as always sir" even when it's me who missed something.

Obnoxious reply but I did this myself so I'm compelled to post it: review apps aren't that hard to implement yourself. You just need a VPS, domain name, and Caddy. Then tell any agent to connect the dots.

This is great advice and it applies to a lot more than just language features. Different architecture, deployment setups, QA approaches are all like this. It's always "approach A is no good", "but company X uses approach A and they're doing very well", "yeah but look at all of these problems they have". Maybe a fair argument but the approach B people also have their fair share of problems...

The subscriptions are per month so I wouldn't use "will the company last" as a deciding factor. On the contrary, if OpenAI really is on its way out then I'd say get their subscription and use the heck out of it while you still can.

Maybe this shows already but my answer would be to use OpenAI just because I think codex is better than the others.

Was gonna say the same thing. GP's description of Fable sounds a lot like my experience switching from Claude Code Opus-4.8 to Codex GPT-5.5.

Looks like "So good the US tried to ban us" is already in the wheelhouse!

My gut reaction was that it does look like a PR stunt. But indeed it might also be a blunder caused by all of their other PR stunts. "Our new stuff is soooo dangerous!!", followed by "The US government believed us and acted accordingly".

Japanese keyboard layout + kmonad is how I cope.

I think the point is that the title makes it sound like people lost control of the agent when really they're in full control.

I do a similar thing where the agent runs in a Docker container and I talk to it with Telegram. It has GitHub CLI access but only with a very restricted PAT. No bind mounts. Jira is pretty clever, though I'm not feeling enough pain with just Telegram to want to try switching at this point.

If "ledger on card" interests you, then you might enjoy Japan's FeliCa cards. They store balance locally on the card so you can pay very quickly, no network required.