resonious

GLM does seem to have security related safeguards but they revolve around just confirming whether or not you own the system being operated on. As soon as that check is cleared, it will do anything.

I think this is just an in-progress shift caused by new technology. Whether it's "good" or "bad" is a separate concern. It looks a lot like how bullying got worse with phones + social media, or how food mass-production results in lots of unhealthy food that people are addicted to. There are a lot of activities we have that are self-limiting, where once we figure out how to remove the limits, there are some negative consequences. Either it will balance out in time (with much pain) or we will just go extinct.

Let's all remember we can return to primitive living at any time. If you don't like the brutality of the rat race, there are many societies out there that just don't play this game. Personally I suspect those societies are also on the brutal side. I'm not sure if we've ever had a truly comfortable existence. Maybe in some brief pockets of recent history. But it's the same human motivation that both drives us to the comfortable times, and brings us back to chaos.

If it's a serious key like AWS or Zendesk then you're probably screwed the instant it gets stolen.

Right - I think a lot of folks who thought they were in it for the joy of programming are realizing that actually it was about the outcome after all. Maybe causes a bit of an existential crisis - you thought you liked programming, but now that there's no money or recognition in it anymore, not so much.

I have PR and only needed a small fraction of this stuff.

If you're bothered by random failures, you probably won't be very happy with a z.ai sub.

Also z.ai doesn't offer Deepseek models.

Go is the best because it has a pretty fast runtime, very fast compile time, rich ecosystem, and is simple to deploy.

Fight me. As a classical software engineer, I hate Go, but in this new era it wins so easily. For web, at least. The subjective stuff about how the language feels is all out the window now.

I suspect publishing an MCP server that provides access to an interesting resource is a better move.

You can also host a chat interface that connects to said MCP server as a convenience. But serious users probably already have their own inference and it's already hooked into other resources as well.

This, really. If I am entertained and learning then I do not care where the content came from.

Of course Claudeish or GPTish ("unusually") will easily push me away. Just like any repetitive or obnoxious tendencies that might appear in human writing.

Hey, I get a 404 from that link.

Sick of seeing "vibecoded!!" in the comments. It is an AI-oriented tool. Do you expect the author to write everything by hand? Do you think a couple of Claudeisms in the docs means the entire thing is unsupervised slop?

Right and so maybe we should stop saying "can't hallucinate" when it can by definition.

Agreed. I think LLMs have actually made good writing stand out more. Now everyone who wasn't a great writer is just producing Claude-isms which are easy to detect. If it doesn't smell like Claude, it's probably good.

I think it's more of an experiment at this point. We don't know whether it's viable or not.

Data centers is a service that itself consumes many goods.

Until an AI can operate in the real world in a completely sustainable way, humans have the reins.

Big yes on this. I do not understand the appeal of skill shopping. The one exception I have is things like the Axiom Apple development skills and e.g. the official Flutter skills. At that point the skills are just docs though. It's either I remember to paste a URL to the official docs or I just install the skill. But shopping around for random skills just sounds extremely unappealing.

You can hire a nanny. I know there's stigma there, too, but I know some "career women" who do this and it works fine. If you're that motivated (and your interests are lucrative enough), you can pull it off.

This is perpetually an issue with the whole field of AI/LLMs. The experience is so personal. Every time I talk to someone about their use of LLMs for software engineering, I'm shocked by their approaches and experiences. They say "X model keeps missing things" when I rely on it heavily for being thorough. They say "Y always gives me the best results" when I can't stand it.

People will see/think that I'm doing very well with my LLM use, and ask me what I'm doing. I tell them, they try it, then later they come back to me saying they just couldn't get it to work.

Marketing that makes them look like they have their heads in the sand.

Why is being statistics/algorithms wrong? What's wrong with that? The "A" means artificial so none of this seems surprising or weird or bad.

Makes it easier to use enterprisey management console type UIs on the go. Also nice for reading large diffs.

Where is the official source for this?

OpenAI's docs still show non-discounted pricing https://developers.openai.com/api/docs/models/gpt-5.6-sol

They do decide on the 5% markup. But as far as I can tell, all other routers just match 5%. Not sure what they're competing on.

You definitely can build an LLM router with only the features you need (even the ones absent in OR!) for cheaper. Openrouter is 5% markup on all token usage. If you're a serious pay-per-use customer of AI, that's a lot of money.

Stripe has such a critical mass, I think SAAS builders don't even shop. It's just of course you use Stripe. It's a like a utility. I think even customers might be surprised to see a non-Stripe checkout when purchasing a SAAS. Might even get worried.

Sol is way cheaper than Fable by the token.

Not surprised at all but there seems to be tons of these kinds of tools and I'm having a hard time picking one. Is there a nice list somewhere? I guess I can ask chatgpt...

Honestly right now I do a lot of development from my phone - I don't have the time to pull out my laptop very much. Right now I use hermes agent and just chat with it on Slack. But sometimes I wish I had easier access to more advanced features, and Slack isn't the best UI for this stuff. So I want to use something like this but am having analysis paralysis.

I wish I had something more methodical I could show. It's all subjective, but GLM-5.2 feels more human to me. Even GPT-5.6 Sol tends to be easier on the eyes for me (though the stereotype of it overengineering and no common sense are still true).

I tried using a new agent service recently and could tell immediately that it's powered by Claude due to the way it writes.

To me, it's just Claude. The other models have their quirks but nothing is quite like Claude.

But even with Claude, it's it's really the prose getting in the way you can install the caveman plugin or tell it to use that "standard technical English" thing.

Yes. You decrement for a few minutes then release if there's no purchase in time. Airlines figured out how to do this a very long time ago.