"Vibe Coding" seems like magic at first but starts falling apart realllll quick at a certain complexity level or if you want to make changes to existing code. If you don't keep an eye on your architecture, you will end up with a bowl of untangleable spaghetti code and some comically terrible engineering choices. That said, agentic coding in the right hands with well defined tasks can have you outputting days / weeks of work in one session; it's not every task, it's not every session, but if you can drive the "idiot savant" in the right direction it's truly an awe-striking and almost alien process to behold.
I've just recently set off time to have a few extended coding sessions, and the results are all over the place.
Guided in a good way for well defined tasks, it has saved me days if not weeks. Given more vague, or perhaps unreasonable tasks, it will quickly devolve into just delivering something, anything, no matter how "obviously" wrong it is.
Very generic, broad and bland presentation. Doesn't seem to have any killer features. No video or audio capabilities shown. The coding seems to be on par with Claude 3.7 at best. No mention of MCP which is about the most important thing in AI right now IMO. Not impressed.
It's a judgment call of course, so disagreement is legit.
The usual test we use is: are the two links different enough to support substantively different discussion? In this case the answer is no, so in that sense they're the same topic.
Another way of putting it is: how much energy would it take to keep the one thread just about the article and the other thread just about the livestream?
Yeah, they sure clicked away from it very fast and kept adjusting the scrollbars. It was confusing what it was trying to display. Furthermore, the prompt contained "Canvas" and "SVG" while as someone with webdev experience these are certainly familiar concepts, i wouldn't consider those in the "casual lexicon" for a random user trying to help a middle schooler with homework. I'm not impressed...
IMO Claude 3.7 could have done a similar / better job with that a year ago.
Seems like sheer incompetence, I’m sure at least the top quintile of my junior year fluid dynamics class could notice it was fishy within a 15 minute meeting… probably more than half could.
I don't always make 6502(ish) errors, but when i do, it's usually the memory address instead of the immediate! It's a very common and easy mistake to make, and i believe Chuck Peddle himself deeply regretted the (number symbol, pound sign, hashtag) #$1234 syntax for immediate values. I made # appear bright red in my IDE, it helps, a bit... Even the ASM gods at Rare fell victim to the same issue!
I ran into a similar issue a long time ago, with the GNU assembler in "intel_syntax noprefix" mode. It has an issue where there's syntactic ambiguity that makes it possible to interpret a forward-referenced named constant immediate as a reference to an unknown symbol, if in an instruction that could accept either an immediate or a memory address. The net result is assembling the instruction to have a placeholder memory address (expected to be filled in by the relocated address of the symbol when linked) rather than the expected immediate. Painful to debug.
TASM IDEAL mode resolves that ambiguity and should've been the standard syntax for x86 Asm in contrast to MASM, and RosAsm syntax is pretty nice too, but GNU as (and its default syntax) is in a wholly different category of insanity that's nearly comparable to HLA.
> Andy Jassy ... said working faster was essential because competitors would gain ground if Amazon doesn’t give customers what they want “as quickly as possible” and cited coding as an activity where A.I. would “change the norms.”
Bruh, no competitor is going to set up an army of datacenters and warehouses on the gargantuan scale of amazon anytime soon... What do customers want? How about fixing your search function accuracy and policing the disgusting influx of scam products with fake reviews!!! Ugh. How about you get AI working on THAT jackknife...
AWS? Possibly. They have a huge head start and haven't lost much ground yet. The warehouses and physical delivery? No way in hell. Any competing physical infrastructure would take a decade from the first shovel hitting the ground today.
The lockout chip(s) are physical chip(s) on the cart and in the console that communicate directly with each other on the cart pins. The CPU is not involved. It's not a "secret key" in the cryptography sense per se.
