Daniel Wonder

Perhaps I was too premature in declaring maxed out modern hardware as the only option for local AI.

Got about 6.2x my LM Studio generation speed testing out TensorFold with DFlash2 and disk caching on my M1 Max.

Time to first token (TTFT) on a cached prompt dropped from 152s

Neo Banking comes to New Zealand 👀

Finally some real competition and hopefully a side order of innovation.

Make FinTech fun again.

What’s happening indeed?

When a novel AI model drops, I immediately want to try it. Not because of what it can do for me, just because it exists 😅

But eventually, you have to acknowledge, the real value is in compute directed to your goals.

Own your intelligence.

If you can’t afford the latest, most expensive hardware, local AI is all about trade-offs. And some trade-offs are more dangerous than others.

Using the best model generally recommended for my era of hardware (Qwen3.8 27B 8-bit on a 64GB M1 Max, Hermes Agent, 64K context,

If you want a real scare, check your AI logs for all of the random websites it has visited in the course of “serving you”

Happy Halloween 🎃

Eurovision for AI. Who is building this?

Slopcore has broken through, and this earworm has been stuck in my head all week.

While Grok Bot is good and has considerably upped my Grok usage, coding in Cursor without Claude API included is a definite downgrade.

For anyone still on the fence of the X subscription…

I did hear there is a Grok model update around the corner though.

Time my agents started pulling their weight a bit more.

That NZ$45,099 512GB Mac Studio isn’t going to buy itself!