Cu3PO42

Anthropic are building out their own bio lab where I believe they will have techs do Claude‘s bidding. I really don’t know how to feel about that.

Even if it plays out that way (which I doubt, we have a ton of requirements around spend tracking), the problem I'm seeing is long term maintenance. I don't want to fudge around with my proxy every time one of the model providers comes up with a new parameter that works slightly differently on Bedrock than it does on Azure.

That said, I am looking into alternatives. Two times in one year is really a terrible look.

You can! And they're delicious.

Some people reject the use of generative AI outright. Some for moral reasons, often based on sourcing of training data, some due to environmental impact, some for concern of how society will change or even just their own job.

I think this is a very fascinating question and one I definitely don't have the answer to.

Here's some lines of thinking that I've gone through:

Aren't our minds abstract in the same way, just running on biological computers?

Say we could achieve whole brain simulation to a level of accuracy where we can actually replicate a human, surely that would be considered a mind and be deserving of the same rights and protections we claim for ourselves? But at the same time, it would be a program and a bunch of data; dare I say 'weights'? I think current day LLMs probably aren't minds yet, but that means there's a border somewhere and I don't know if we'll realize when (if) we cross it.

I find it very interesting that for both these models we such a clear progression of better images with higher thinking levels from 'hardly useful' to 'pretty nice'. I feel on many other models low and max are much closer.

Cutting prices by 50% as compared to 5.6 prices is exciting. GPT-6 Luna at $0.10/Mio input tokens and $0.50/Mio output is positively insane.

EDIT: this doesn't say anything about availability on either Azure or AWS. I'm assuming it will show up later, but it would be interesting if it didn't.

I didn't get that either until I read this comment. I read "pushin" as one word, figured it was a made up proper name for a product.

Once upon a time, I, too, had a domain where the TLD was part of the actual name and required to read it correctly (think something like foobar-pl.us). In my experience this left most people confused and I abandoned that quite quickly.

It’s currently 50% off on OpenRouter even.

Thanks for pointing that out. I tried the Codex App before but didn't see that.

I want to like the app, but I'm not sure if it actually fits well to my use case. With my current setup I need to fully quit and restart it if I want to work on a different project (to get it to use a different API key) and I cannot work in two threads belonging to different projects at the same time.

Also I generally prefer to handle sandbox the entire agent and disable its internal safeguards. Beside any doubts regarding the quality of the relevant sandbox implementations, I have just gotten my projects to work better this way.

This does look legitimately exciting. A surprisingly large pain point when doing agentic work has been commenting on something in a larger plan document. I always find myself summarizing the surrounding text to contextualize a comment when all I really want to do is highlight and click "add comment".

Unrelatedly, I have been looking at Zed to centralize my agentic work at $job, where we use different API keys per project to better attribute spend and control model availability based on per-project data protection controls. All of the standard UIs I've tried for this don't really work, but the CLIs mostly do. Using ACP in Zed I was able to bridge that into the UI world and I'm quite happy with it.

I signed up for the beta and I look forward to trying it.

I loved garnix and I’m sad to see the service shut down. That said, open sourcing the platform is the best way to do it I can imagine. I wish the team success at Shopify.