Je t’assure que ce besoin qu’on certains français de montrer leur capacité de parler l’anglais, de nommer leurs entreprises avec des noms à connotation anglophone, etc. est considéré très gênant ici du Québec.

J’imagine que c’est de plus en plus facile de le faire avec l’aide de l’IA!

That's extremely weird. I don't know of another place that does that aside from Quebec, and it's extremely illogical on its own merits.

"Extremely illogical". Okay buddy.

What other place do you know of whose context is the same as Quebec?

I use local LLMs on my Mac Mini.

Otherwise DeepSeek Flash 4.1 is dirt cheap (other "Flash" models are not that expensive either). I pay (very few dollars) out of my own pocket.

There are many things where having an API Key is necessary.

Maybe I’ve missed the boat though: is there now a method to use an api key to access a subscription?

You can't use an API key on subscriptions, but I've gotten around it using the `codex exec` command to run requests outside the CLI or GUI if you're already authenticated on that machine. Won't work for all cases, but I've never ran into a limitation in my use case of not having an API key.

I’ll look into this. But there is no universal solution. I find this to be quite limiting. I understand this is on purpose. If you want to automate, you need to pay more to have an api key.

It’s a good thing we have access to those very cheap and useful Chinese models.

> I use local LLMs on my Mac Mini.

which ones do you use?

I use the following models:

  - Qwen3.5 9B
  - Qwen3.6 35B A3B
  - Qwen3.8 27B
  - Gemma 4 26B A4B
  - Gemma 31B
  - Muse Glimmer 30B

I have 48G.

The MacMini is used solely for inference. llama.cpp + llama-swap.

People are saying local models are crap and serves no purposes.

I use them to help me spell check, write emails, write text messages, write JIRA tickets, write PR comments, etc.

I also use them in coding agents to complete different tasks.

I find them quite useful!

Thanks! I have two mac minis: one with 8 gb and the other with 24 gb (left with 17 gb useable ram); I can't run any open model on them. So, ordered a Mac 5 pro with 128 GB. Can't wait for its arrival.

128G of RAM? I envy you.

You will be able to run some pretty impressive models locally. Good for you.

Didn’t Israel use AI to target Hamas agents?

You would think, following the absolute horror that was, that any civilized nation would not use such a tool in such capacity.

Or rather, it showed it was working wonderfully for cases where war crimes is a goal.

Why wouldn't they? There's been very little repercussions for anyone so far. Apart from the Netherlands bracing itself for sanctions from America because the ICC dared to suggest someone might have done something wrong.

Check out nono.

They already exists. You haven’t been invited? Hmmmmm

It’s not that bad: https://news.ycombinator.com/bestcomments

I really like that page. I've recently attached a search feature to it with corresponding atom feed.

https://hackertrain.future-secured.com/?q=great

One thing that's changed over time is a lot more usage of "scare quotes" especially now (Gemini agrees https://share.gemini.google/UiUf0jttZLVD ). It's an interesting phenomenon, Abloh started using quotation marks consistently in his fashion branding since 2012. https://blakecrosley.com/blog/design-philosophy-virgil-abloh

Next step would be to attach an AI to all the /bestcomments.. if someone needs help doing that I'm here. Really, that's a task for the mods.

Why they instead of a microVM?

MicroVMs make the most sense to me, as they are the simplest and cleanest abstraction. I personally use VMs with a mounted github repo and found it to be the simplest mental model. I block all network access except for the domains that the agent needs to talk to, and I remove sudo. Since its all scripted, the VM is easy to drop and recreate and I know exactly whats installed on it.

Drop is interesting because it is thinking about the approach differently - basically an extension of the user's existing userspace. This prevents files from being inadvertently deleted by the agent, but it doesn't prevent the agent from uploading files that it shouldn't be.

How does it compare to kagent (https://kagent.dev/)?