[quick reply as I have to run out] On 12/12/25 17:21, Neil Cherry wrote:
I just tried the same asm 68K code query that triggered the initial post with Claude, code is better but Gemini made the assumption that the DUART had a 3.6864 MHz Crystal. Claude doesn't state this assumption but does get matching settings. I didn't state that in my initial (very vague) requirements. So, +1 for Claude. :-)
If you think about it, it would be surprising if it hadn't guessed that. Why? Because the thousands of conversations and manuals ingested by Claude that talk about DUART designs all mention the use of a 3.6864MHz crystal. That's how the whole thing works. It's not hype, it's real. It's just in its infancy.
Actually that is what a lot of us are doing. We're 'training' the AIs for the big corporations. Scares me.
As well it should. And you know that blank stare that you get when you explain to someone "if you receive value from an online service and you haven't paid for it, YOU are the product"? They (99.44% of the public...if not more) are every bit as clueless and oblivious about this situation. Bread and circuses.
I'd love to setup a home AI. Just have too many other things to do.
I understand. I only took the time to do this because, at the time, I was desperate for a break from what I was doing. If you'd like to duplicate what I've built, I can provide guidance; it can be done in an afternoon after the (cheap) hardware arrives. Then you can do stuff like this: ----------------------------- ra$ ollama run llama3.2
Explain the relationship between semiconductor band gap and valence band electrons. Answer as Valley Girl.
Oh my gosh, like, fer shure! So, you wanna know about the relationship between the semiconductor band gap and valence band electrons? Like, it's totes important! Okay, so like, when a material is in its pure form, it's got these energy levels, right? And one of those energy levels is called the valence band. It's where all the valence band electrons are, like, hanging out and stuff. Now, when we add impurities to this material, like, say, phosphorus or boron, they can replace some of the original atoms in the lattice. This creates these defects, like, holes in the structure. And because of that, some of those valence band electrons get excited and jump up into, like, a higher energy level called the conduction band. But here's the thing: there's this energy gap between the valence band and the conduction band, right? It's like, a forbidden zone where no electrons can go. This is called the band gap, fer shure! So, when we add these impurities and create those defects, they kind of "push" some of those valence band electrons into the band gap. Like, it's not possible for them to go any further up, 'cause there's this huge energy barrier in the way. Now, when you're trying to conduct electricity, like, what you want is for those conduction band electrons to flow freely through the material. But if they can't get into the conduction band because of that band gap, it's like, super hard to get anything done! But don't worry, dude! Because we can control the band gap by adjusting the amount and type of impurities added. It's like, a delicate balance between getting enough electrons excited to conduct electricity and not so many that they just, like, overheat and stuff. So, in summary, the semiconductor band gap is like, this energy barrier between the valence band and conduction band that affects how easily those conduction band electrons can flow. And by controlling the impurities and defects, we can kinda tweak that band gap to get the desired conductivity, fer shure!
Send a message (/? for help)
-Dave -- Dave McGuire, AK4HZ New Kensington, PA