anamexis

Claude Code Web does all of those things for me with the GitHub connector enabled. I did have a lot of song and dance to get the permissions right though.

I have been working on a 100% vibe-coded magit-style jujitsu porcelain for neovim. I cannot emphasize "vibe-coded" enough -- I have not read a single line of code here, nor do I know much about neovim development in general. All that said, it's been working pretty well for me the last couple weeks!

https://github.com/micahbf/maju.nvim

Right, so if they were able to get a discount in UAE…

If all of the storage is used up by models, users will need to buy proprietary cloud storage for their own content.

What point are you trying to make?

Retirement is the withdrawal from active working life, i.e. having a job. It is not a US concept.

> All the docs are already in its training data, wouldn't that just pollute the context?

No - there is a reason that coding agents are constantly looking up docs from the web, even though they were presumably trained on that data. Having this information directly in context results in much higher fidelity than relying on the information embedded in the model.

"With instructions that would be clear for a reverse engineering specialist" is a big caveat, though. It seems like an artificial restriction to add.

With a longer and more detailed prompt (while still keeping the prompt completely non-specific to a particular type of malware/backdoor), the AI could most likely solve the problem autonomously much better.

Why, though? That would make sense if you were just trying to do a comparative analysis of different agent's ability to use specific tools without context, but if your thesis is:

> However, [the approach of using AI agents for malware detection] is not ready for production.

Then the methodology does not support that. It's "the approach of using AI agents for malware detection with next to zero documentation or guidance is not ready for production."

Why is that a pet peeve, though? Seems like a win/win.

Salesforce acquired Heroku 15 years ago.

Everything HTMX does could be "just" done using JS - this is self-evident. The whole point of HTMX is to enable features like this directly in HTML.

Did you read the OP?

That is not IP Geolocation.

Maybe I’m missing something, but Google does not offer an IP Geolocation service or publish their database.

The point is that once Siri is switched to a Gemini-based model, the baseline presumably won't be low anymore.

Why would it be a breaking change? Just continue assuming JSON if no Content-Type is provided.

Giving guidance on which one should be used and when is well within the scope of external parties.

Every loss leader's purpose is to build up market share.

Why is it poor behavior though?

Could you use multiple coils for different bands?

It is updated on their actual home page, though. There is clearly no intent to mislead people.

https://iquestlab.github.io

And neutrons are neither.

This hasn’t been true since Ruby 3.0. Keyword arguments are a core language feature with their own semantics.

It would seem that in T-Ruby all arguments are keyword arguments, although they don’t really spell this out.

https://type-ruby.github.io/docs/learn/functions/optional-re...

Structural typing like this is completely compatible with the concept of duck typing. Indeed, it's basically doing static checking of duck typing.

Is Sorbet not what you’re describing?

And RBS is officially part of Ruby…

Sorbet is backed by Stripe.

Why is it important to be a separate layer that compiles to plain untyped Ruby?

extremely cool, thank you!!

I appreciate that it's brand new, but I'm still very interested in knowing about what sets it apart, even if that is all just vision at this point. What does "extending what's possible" mean?