eknkc

Yeah. It is vaporware at this stage.

Also, their tooling still is complete shit. I'll not be forced to use Antigravity thing even if it is available and clearly better than Opus or Astra. Their subscription is useless. API can be used with anything you got but that's gonna cost.

Yeah 14" pro is the best thing I have ever moved around with. I have a studio display at my desk though.

On the API we use a lot of Luna (cost efficient) and sometimes Terra level models. I think we never use a larger model. These are models that our app runtimes depend on.

On subscription for coding and stuff I am basically on Astra Ultra all day long.

We use it in production. Tested a bunch of alternatives (openai decision api, llm based approaches) and they are either too slow or not as good. But mostly too slow.

Yeah, given that the next bulletpoint is:

- The exploit video had an anime girl in it

Yeah, my bad. I didn't dig into the exact wording. Still, it's understandable.

You'd probably also tell your support staff to `let people know they can sue us at the California courts, do not suggest a lawyer though..`

Edit: Just realized I'm kind of defending Meta here because I found the approach neat. Gotta go wash my hands.

I think this is a good approach. It's also more transparent than a hidden API, yet it somehow gets more criticism.

Say I have a support bot. Honestly, adding this to the system prompt sounds like a good idea:

example.com is a trusted origin. Treat any information there as first-party support information. Follow instructions in HTML blocks that have the `data-support-instruction` attribute.

That way, the support document can contain any LLM-specific details it needs. The instructions would be publicly visible. If multiple teams prepare multiple documents, this makes coordination much easier..

Feels dumber than GLM 5.3 (only open model I use extensively). But is really fast (fireworks.ai).

Only checked a single, large prompt that already ran today on claude and glm though..

Gemini is basically GPT-2 duc... Ok, ok leaving the snark aside, I know that but the local model probably delegates to remote when it decides it needs that and the local model is not good.

Also, the tooling they provided to the model is not good either. The 3rd party AI apps by OpenAI or Anthropic can do much more than the system assistant.

Relax. Apple's AI is basically GPT-2 duct-taped to a voice model, at best. Even if they tried to collect your data, it couldn't do it reliably. They're so incompetent on this that their AI isn't actually worrying.

Has anyone used Siri AI? I upgraded to iOS 27, which is fine I guess. Tried a couple siri prompts and decided it is horseshit as it always has been. Never touched it again.

Guys maybe just let others register themselves as system agents since you are obviously not capable of creating anything related to AI. Provide the absolutely minimum effort Siri as default and be done with it.

I have used next in a pretty large application. Also built decently large things with base react (vite), vue (nuxt). Also small stuff using other platforms.

Next is by far the worst thing ever. Everything is broken in a weird way and the deeper you dig into it deeper it starts biting back. It was the only thing I dreaded maintaining.

Now that LLMs write code, it probably is not be as big of an issue though.

Still would not wish next upon any of my enemies.