The company standard for servers is RedHat 10. RedHat 10 does not support 32 bit applications.

The legacy app is running happily on RedHat 9.

...laura

I support a legacy app that was written back in the 1990s. It originally ran under VxWorks with custom hardware, variously 68k and PowerPC.

The first port I did was to Solaris. No byte-order issues and I kept the 32 bit ABI. It worked well.

When the Powers That Be decided to ditch Sun hardware and Solaris in favour of x86 and Linux I ported it to Linux. Parts of the code weren't byte-order clean, but I worked through them. The code is heavily 32 bit dependent and I never did create a viable 64 bit version (I tried, believe me...), so it runs on our last 32 bit server in the data center. The service it supports is slowly dying so there's no business case to spend any more time or money on it. If the business case existed I'd apply what I've learned in the meantime and rewrite it from scratch anyway.

The Linux port was initially unstable. It would run for a random time, hours to weeks, then two threads would deadlock. After a couple of years of letting it run and watching it crash I traced the deadlock to an "optimization" that didn't actually do anything, with an if statement that had about a one in a trillion chance of going the wrong way. I removed the optimization and the application has been running fine ever since.

...laura

Ever heard the song "I ain't gonna give nobody none of my Jelly Roll"?

Do you have any proof other than statistics which you decry in the case of AI that chemo works? What if my Dad just got weaker and weaker and the cancer didn't stop or slow down for long enough to get over the side effects?

What if medical diagnosis of depression and addiction led to a whole cocktail of antidepressants, and rehab, prescribed for my brother, yet he remained depressed and addicted till the end? What if instead of trying to treat him with AA homilies they'd legalized cocaine and taught him to manage it?

Am I free to talk about my own philosophy, or are my words alone so dangerous you must use censorship (and how well did that work on Trump, RFK Jr, etc.)?

Is that because I spent my youth trying to figure out how to do natural language processing, and now they solved it?

Do you realize how hard it was to get any AI to even understand your questions and generate natural language answers without grammatical mistakes, 100% of the time, before the Attention mechanism?

Remember Cost Of Living Adjustments? What if your income goes up with rent, etc. so that your real purchasing power is unaffected by nominal inflation? If you automatically convert prices to units of purchasing power can we remain unaffected even by nominal hyperinflation?

So why are so many slashdotters adopting the position that information should not be free and everyone should be punished instead of saying let everyone copy?

Is it because I'm unrepentedly troll-hearted, and people's feelings get hurt, so they just want to silence me? Do you get butthurt at my words on the internet because they bring up inconsistent things that cause painful cognitive dissonance which you'd rather ignore until it comes back in form like Troll Trump being elected president?

Do any of the Dems you named understand that money is not zero-sum and the Fed can create money faster than prices rise?

What if you index incomes to price rises so your food always costs the same in terms of your real purchasing power?

So is "information wants to be free" back, but now slashdot is against and corporations support it?

How often are teachers confidently incorrect?

Beyond the AI DS, what if it's standing on the shoulders of giants?