Does it? I'm not sure I'd necessarily notice but I haven't found it noticeably worse.

me feel that it needs some tweaking - it's a little annoyingly cute (and could be even terser).

same. I use pi - and anthropic pricing change have made it usuable with Max. Codex works pretty much the same, not need to change development practice... apart from no 429s (so far).

had been using claude max/opus with pi and the results have been incredible. Having pi write an AGENTS.md and dip your feet into creating your own skills specific to the project.

With the anthropic billing change (not being able to use the max credits for pi) I think I have to cancel - as I'm whirring through credits now.

Going to move to the $250/mo OpenAI codex plan for now.

Regardless of which harness you use, asking your agent to self-edit its own .claude (and to put it in the repo itself so you see the changes) is the single biggest impact change you can make in terms of compounding improvement. Couple this with telling it to create skills for /garden (clean up drift based on what changed this session), /handoff (garden, create ant skills to resolve friction encountered this session, and write a summary of the session and note for next agent), /takeover (read the latest handoff file). Since doing this I’ve completely cured my session-abandonment anxiety and can confidently swap to a new session at < 20% context usage without feeling like I’m talking to someone who just woke up from a coma.

Can you provide more details on these skills?

Honestly… just paste my comment into the prompt and you’ll get it 80% of the way there. The important thing is to seed it with instructions so it will iteratively improve its own instructions each session.

I was looking into this as well since Claude models are costing too much with the Extra Usage changes.

Is OpenAI codex not also charging by usage instead of subscription when using pi?

pi is what OpenClaw runs on, and so far OpenAI seems committed to it. No telling how long it will last.

I think people are more concerned about SpaceX getting the raw deal here.

And specifically that if the music is about to stop SpaceX has an implicit government backstop

It doesn't have to; the government's rescue of GM in 2008 killed a bunch of brands that they owned.

But given the current administration, I don't have a lot of faith in the government looking out for anyone else's interests here.

And TARP destroyed 4 of the 5 largest investment banks in the US, but it still left a bad taste in a lot of people's mouths

Starlink is about to get billions and billions from the BEAD program, on top of this.

You’re really asking whether anyone at a private company is publicly speaking up against the famously emotional and vindictive owner?

Yes. People are saying they’re worried that the poor private investors of SpaceX are getting the short end of the stick.

That seems like misplaced concerned for an investor class that really aren’t suffering.

This thread specifically excluded the big investors, but they too have nothing but loss popping the bubble: Musk has been talking up the value of their investment. If they criticize in public, they’re just costing themselves money — much safer to sell and walk away.

Well, no, the worry is that xAI's bondholders, who are also Twitter's bondholders, will be indemnified from any loss on those bonds at public expense because they are now also SpaceX bondholders and SpaceX is a national security interest of the US.

> bonds at public expense because they are now also SpaceX bondholders and SpaceX is a national security interest of the US.

If our elected officials have done a poor job diversifying risk by not just depending on one single supplied, they are to blame and we should hold them accountable.

But, is that even the case?

I think unsavory business practices actually affect approximately everyone, even those not directly connected to any one particular instance of unsavory business practices.

Culture exists, after all.

Well this was just announced, and I'll be surprised if nobody gripes about a $2T dilution of their equity.

I think one of the things that will need to be embraced is carefully curating .md context files to give the prompts better/shared direction to contributors. Things like any new feature or fix should include a test case (in the right place), functions should re-use existing library code wherever possible, function signatures should never change in a backwards-incompatible way, any code changes should pass the linter, etc etc. And ideally ensure the agent writes code that's going to be to the maintainer's "taste".

I haven't worked out how to do this for my own projects.

Once you've set it up it's not too hard to imagine an AI giving an initial PR assessment... to discard the worst AI slop, offer some stylistic feedback, or suggest performance concerns.

> the European Union was seen to be a good thing in the eyes of the archetypal Brit

It wasn't, hence Brexit. We were dragged in via a Customs Union against the will of the British electorate at every turn.

Read the rest of the sentence.

The £100k threshold is such an economically illiterate policy for society. The GPs and lawyers I know are working ~3 days a week to avoid it, so much economic output and taxes missed out on.

and most don't live in the neighbourhood, city or even state (in tech anyways).

> This is great for HMRC because it collects 10 times more than what the publican does

WTF.