The fix for a spiralling AI bill is rarely a cheaper model
Most AI cost overruns come from asking the same easy, judgement-free question over and over through an expensive interface, not from asking anything genuinely hard.
My Mac Mini is going back to the shop
Three separate experiments on the same Mac Mini all pointed at the same conclusion: free and private don't matter if the answers are wrong or don't arrive at all.
Self-Refine Without a Repetition Penalty
A controlled case study: the same recursive self-improvement loop, on the same local model, six and a half hours each. One run collapses into repetition within forty cycles. The other holds clean for all two hundred and one. The difference is a single sampler setting.
I ran a local AI model through 179 rounds of self-refine. It collapsed. One sampler setting fixed it.
An unguarded local model collapsed into repetition after 179 rounds of self-refine. Adding one sampler setting and rerunning the identical task produced 201 clean cycles instead.
Becoming a CMO: What You Actually Lose When You Stop Doing the Work
Career advice tells you what you gain on the way to CMO. Nobody tells you what you trade away - and how to stay close enough to the work to keep your judgement calibrated.
A 35-billion-parameter model now runs on a $599 Mac Mini. That doesn't make it useful for everything.
Ternary quantization gets a 35B open-weight model running on a base Mac Mini at reading speed. It still confidently got GEO wrong, which is the more useful finding.
How We Grew Marketing Sourced Pipeline by 20% in One Quarter
Why judging marketing by what happened this quarter is the wrong lens, and how Redgate grew marketing-sourced pipeline 20% anyway.
Human Beings are Holding Back Machine Learning
Machine learning tools have been accessible for decades. The real shortage has always been people who know how to use them properly.