Introducing a new side project called Model Regression. It tests daily Claude, GPT, and Grok on various benchmark statistics to determine how well its performing and to identify model degrades over time. @edskoudis had an idea for model testing before they conducted offensive testing to ensure the model was performing as expected, and @BlasikRandy pushed me down this road with actually going and doing it. The main intent here is the frontier models will experience outages, issues, bugs, intentional/unintentional nerfing of the models without notice. You can't typically trust day to day activities in these models for stability, so leveraging this on your daily routine to see how well the model is performing for that day is something I'll be using everyday. Runs every morning in my DGX sparks environment and automatically updates with how well its performing. Enjoy! modelregression.com/ Also open-sourced the project, can run on your own server as well and look at the benchmarks and how they are calculated: github.com/HackingDave/model…

👀

Just spoke with a customer service rep at @ArcBestCorp to get some tracking details, and holy cow, that had to be the friendliest, quickest, best experience I've ever had with a shipper. 👏👏

Who keeps breaking the internet???

Not me tweeting again about what a hot pile of trash Quickbooks online is. I should be in bed, but instead I’m trying to make a broken product do things the desktop version had no problem doing.

"It looks like you need help with your hosts file"

It’s 2024 and we still have voiceovers where they refer to backslashes in urls 😒

I might be biased but think this Cavs intro is 🔥

Really trying to watch the Cavs game but damn this red court is hurting my eyes

I get a new notice of a data breach on a pretty regular basis now. Seems like credit monitoring should just be part of the Bill of Rights at this point 🤷🏽‍♂️

First workout powered by @wehackhealth Overclock 🚀

Overclock from @wehackhealth showed up about an hour after I finished my workout. Gonna have to wait til Monday to try it!

That was quick!

Whoever was running @TowerLightsCLE and syncing it to the @311 show lights tonight was great! @pnut @NickHexum

It’s that machine @HackingDave won’t do in public 😆

Hey @hulu - I rebooted my cable modem and my ip changed because it’s dynamic… but suddenly you think I’m not home anymore and only give me 3 more changes? Does this happen every time my ip changes?

Self checkouts are my nemesis. Don’t make the beeping sound if you didn’t actually acknowledge what I just scanned, and then accuse me of trying to steal 😤

Had a fun time at the @onepeloton studio today for a ride with @emmalovewell that was also my 1,000th ride. #peloton

We had a great time at our annual @cavs Court of Dreams event yesterday! Our employees & clients played a competitive game on the home court, followed by a reception and the Cavs vs. Heat game. We are proud to be the official #cybersecurity provider for the #ClevelandCavaliers!