I love this, thank you posthog for being great

It’s probably just that they started before gpt 5 was released. It’s a good judge.

Please for the love of god, if you work at cerebras, please put this on an API for me.

I’ve used sgpt and really liked that as prior art

Versus fleshy children, silicon children might be easier or harder to align because of profit interests. There could be a profit interest to make something very safe and beneficial. Or one to be extractive. In this case the shape of our markets and regulation and culture will decide the end result.

History tells use there will be colonization for a century or so before things quite down.

This is a horribly written article littered with logical fallacies. Nearly every point is just a random fact about gambling that doesn’t add to the argument.

- fanduel owns networks. So what?

- gambling taxes = corporate taxes in MD. This is misleading as state level corporate are effectively $0

- 20% of Americans have placed a bet. So?

I have never done sports gambling myself but this article fails to convince that it’s a problem

Amazing work! The UX is great.

GPT-5-codex does more research before tackling a task, that is the biggest weakness for me not using Composer yet.

Could you provide any color on whether ACP (from zed) will be supported?

What actually is this?

A framework for optimizing LLM agents, including but not limited to RL. You can even do fine tuning, they have an example with unsloth in there.

The design of this is pretty nice, it's based on a very simple to add instrumentation to your agent and the rest happens in parallel while your workload runs which is awesome.

You can probably do also what DSPy does for optimizing prompts but without having to rewrite using the DSPy API which can be a big win.

>What actually is this?

Based on the number of emojis, I doubt the author even knows.

Apple and Google couldn’t take 15-30% that way