That tells us nothing, nothingburger speculation. However, Apple had that major incident in its history when they made Adobe mad when they went out and shopped for final cut pro, color, and a handful of compositing apps. Didn't turn out well for Apple at the time.
I had to disassemble some furniture as well recently. It had one and a half million screws and whatnots and since it was going to recycling center anyways I figured out sledgehammer was as good tool as any. Turns out it was better than _any_, ultrafast (take that claude!) and a ton of fun.
Sure, I've been here for almost 20 years. It doesn't change a fact it sounds stupid. I asked two colleagues from Japan and they both agreed this probably wasn't done by a japanese person.
Sarcasm hat on - You know what, if LLMs were so infallible at coding and engineers useless for hands-on, then why even bother with anything except asm or even skip the mnemonics completely and go straight for the binary? Why even bother with abstract code when abstraction is now your LLM.
That's the million dollar question. Do you/we/us have tests that cover everything which covers QA as well? If such a mythical beast exists, maybe from remnants of ye olde TDD past and hasn't been modified as such.. then maybe this would be possible to do as such.
I don't want to knock you down as most have already did. In-fact it's a useful exercise going forward in exploring how to work with AI. It's here, we're all going to use it one way or the other. Zero issues with that, in-fact kudos to going through the pain of it all.
Now, having gone through several such endeavors originally myself, albeit with internal tools and systems (as an exercise), I've noticed that while all my tests passed with flying colors the rewrite itself was broken even on basic functionality or missed a ton of details. It was in effect useless when I dived into it. Initial tests also showed massive gain in performance, and I know people who were involved aren't really dumb so something smelled funny. Turns out all those things left out and honestly... moments were the key ingredients.
What I did learn from those beginning explorations though was that one-shotting, grand architecture or source up-front, master plans up-front.. all these do not yield good results - YET. Who know what we'll see in few years though. What I did found that works (FOR ME, nota bene) is to keep the design and checklists for myself, written by myself and then do a small piece by piece.. as if you would if you were coding alone or if you would waterfalling a small team of talented juniors. Then, suddenly super happy results come out, but then it's mostly you driving all the way where llm writes code and offers advice (which for the most part you ignore). It's a happy place for myself at least. It's then truly unlocking yourself to the mythical 10x.
Rewriting a large proven system with decades of ultra expertise behind it, which I don't have, is guaranteed not to end up the same 1:1 replacement. If you found a recipe for that - please do share.
akshually, it's also more closer to 500-1,000x. You can't look at clock speed only. Processor architecture makes all the difference. Pipelining, SIMD, memory bandwidth, blablala, everything got way better. Better approximation would be to use something like a synthetic benchmark or just (theoretical) FLOPS of each.
while impressive as a standalone number, half of it is in US. It launched a year ahead of competition at a much lower price and was when XBOX Live came about. And even with that - it couldn't make a dent in the dominance of of Sony and Nintendo in Japan, where in some cases it was fully discontinued early on and it was s series of missteps that led to where we are today. Microsoft never knew what they were doing. When it seemed like there was a success at hand, it was serendipity rather than Microsoft. Microsoft and their fundamental lack of understanding of gaming is what led to all of that.
This reads like corporate death rattle. Microsoft never had any clue what it takes to make a console - a console. Now it seems they've also completely lost the plot on what makes a business - a business. They should've been Steam, instead they ran out of it.
follow me at: https://twitter.com/keyframe
dominik.susmel (at) google's popular email service