indemnity

I build AI agent runtimes for a living. That doesn’t mean I like to set my money on fire due to the current supply and demand mismatch.

Apple never drops prices, never. It will go straight into their margin.

I have an M1 Max but I am not paying 50% more than a few months ago to upgrade.

I have bought Apple laptops since 2004 but I can’t justify the current extortionate pricing, so I’ll sit it out (permanently if need be).

We had the X-Trail AWD version of this. The plus side was getting around 850km to a tank of petrol. However, the EV-only range was very poor and the engine was quite harsh sounding when it spun up. Super happy to get rid of it and switch to BEV.

Happy we made the switch to all EVs + solar this year. Knock on effects on the economy are going to be brutal though.

Every damn vibe project: “Catchy hook, descriptive explanation”. Like they’ve all got their own marketing team now.

I am on the Claude Max 20x plan, and this still happens when using Fable 5/Opus 5. I would run out of weekly quota in 2 days, whereas Opus 4.8 would last the entire week, and sit at about 80-90% at the end.

I have a 9950X3D and an RTX 4090 in a 10L case (FormD T1).

Water cooled but it does get a bit loud when I play games, silent for regular usage.

The return of CDOs?

I put in 2 CAT6 wires to every room in the house (4 in my office, 4 in garage), with one big PoE switch in the garage.

Everything with an Ethernet port is wired, wifi is for phones and tablets only (a few UniFi WiFi 6 APS).

Works great!

Internet has never dropped for me while working, family loves the always working NAS streaming via wired Apple TV.

Using ASD-STE100 is in my system prompt, not just CLAUDE.md which basically never gets followed.

I actually converted it from the PDF into an explicit skill with the word list inline as well as the main rules.

Works a little bit, but give it a bit of context and the model’s training takes over and it starts talking like a dictionary-huffing crack addict again.

It’s a model problem and no amount of harness hacking seems to fix it.

I mean I do the same at work where we currently use Anthropic, but we are also on a token optimisation drive so it’s getting hard to justify spending even more tokens cleaning up after Anthropic’s garbage by paying Anthropic more. We have started having users use GPT 5.6 Sol to compare quality and effficiency over Opus. Fable not happening at work because of the data sharing clauses and the completely nuts pricing.

How long will the petrodollar remain a thing with the current diversification of energy sources proceeding apace internationally?

Listening to Americans talk about energy and vehicles feels like going back in time, they’re stuck in the past and things that worked then and the world is rapidly routing around them. Quite sad to see.

I’m a heavy LLM user but if someone gives me an AI-voice argument and presents it as their own, I reflexively dismiss everything they say going forward.

I can prompt the LLM myself thanks.

And where would we put this? I don’t want to write that out every prompt. CLAUDE.md is a joke, it has little to no effect.

Basically, I’ve gone from supporting them to hoping someone else wipes the floor with them.