Investigating Software

5 min read Original article ↗
Pete Houghton

I explore technology and how to build software that is reliable, safe, and affordable, quickly.

by Pete Houghton peterhoughton.com LinkedIn

  • Glowing Evals

    · ai testing evals banking critical thinking

    There's a fascinating scene in the series "Chernobyl", where the engineers report that the radiation level is 3.6 roentgen). The number, they explain, is high but not terrible for a nuclear accident. Initially it's reported up to soviet premier Gorbachev as the equivalent of a…There's a fascinating scene in the series "Chernobyl", where the engineers report that the radiation level is 3.6… more »

  • Claude is good but is it x6 better?

    · testing automation ai evals banking payments

    Because that's how much more it can cost! As a 20x Claude code MAX subscriber I'm acutely aware how much tokens cost. "Yes you’re absolutely right, let me fix that" (Pete sets fire to a pile of cash) So that’s why I've been comparing the costs for inference both from different…Because that's how much more it can cost! As a 20x Claude code MAX subscriber I'm acutely aware how much tokens cost.… more »

  • Who would have thunk it, coding was automated before testing!

    · testing automation ai evals

    It’s not that analysis, solution design etc are automated but the writing of the code itself is now fully automatable. "Testing is also automated!" you say! well in a sense, yes, but much like how the broader/deeper work of analysis and system & solution design is still a human…It’s not that analysis, solution design etc are automated but the writing of the code itself is now fully automatable.… more »

  • Vimes Boots & why the right AI evals could save your project

    · ai automation cloud evals illusion investigation

    "The reason the rich were so rich, Vimes reasoned, was because They managed to spend less money" Sam Vimes, from Men at Arms by Terry Pratchett. The theory goes that richer people can afford a pair of boots that last longer before repair or replacement than poor people, who can…"The reason the rich were so rich, Vimes reasoned, was because They managed to spend less money" Sam Vimes, from Men at… more »

  • Be the Human Out of The Loop to avoid being The Fall Guy

    · agile ai automation breaking things critical thinking deep learning

    Do you know what a fall guy is? the answer is you. Why? Because when you're told that there is a human in the loop means... there is a you shaped person to blame. So, while you are working harder than ever, using the latest tools money can buy or tokens can build someone has…Do you know what a fall guy is? the answer is you. Why? Because when you're told that there is a human in the loop… more »

  • The best book on AI Agents for the layman

    · agile ai banking breaking things bug gothic

    Alan J. Portis once quipped that: "the best book on programming for the layman is Alice in Wonderland, but that's because it's the best book on anything for the layman". In the same theme, I'd like to suggest an addition to your library, the best non technical book on AI Agents…Alan J. Portis once quipped that: "the best book on programming for the layman is Alice in Wonderland, but that's… more »

  • AI Agents & the aptly named Butt report

    · agile ai automation banking questioning

    It's August 1941, during the opening years of WW2, the axis powers had conquered much of mainland Europe and the Allies were desperately trying to limit the capacity of the axis military industrial complex. They did this with little feedback on their success much like some…It's August 1941, during the opening years of WW2, the axis powers had conquered much of mainland Europe and the Allies… more »

  • Validators as coding agent specifications

    · ai automation banking deep learning human payments

    I was raised in a world full of rules, like all of us, though as I grew up in a military family in and around military bases so maybe a bit more so for me. As a parent myself, rules are at play "no son you can't bang our wooden table with an old hammer". Even the business world…I was raised in a world full of rules, like all of us, though as I grew up in a military family in and around military… more »

  • Bucket of trouble, if you don't keep an eye on AI

    Ever tried to get a teenager to do more chores around the home? For those without this joy in their lives, I’ll let you in on a secret it goes down like a bucket of sick. You can sometimes cajole them, sometimes bribe them and even threaten them (We’ll take away your laptop!)…Ever tried to get a teenager to do more chores around the home? For those without this joy in their lives, I’ll let you… more »

  • Can 'reasoning' LLMs help with recs data creation?

    · ai deep learning records

    A nervous tourist, glances back and forth between their phone and the street sign. They then rotate their phone 180 degrees, pauses, blink and frown. The lost traveller, flags a nearby ‘local’ (the passer by has a dog on a lead. “Excuse me…” she squeaks, “How may I get to Tower…A nervous tourist, glances back and forth between their phone and the street sign. They then rotate their phone 180… more »