Learning chords with ChatGPT voice conversations

Asked ChatGPT voice* to quiz me on chords while I was walking around the neighbourhood.

Voice recognition was good, response time was good. I didn’t love the “connecting…” stage to kick of the chat. And had bit of a buggy launch, but once started it was solid.

Initially it would ask a single question, I would answer, then it would say “do you want to continue?”. I asked it to skip that and just keep going until I left, which it did remember to do.

It kept pronouncing Bb as “beebee”, and Eb as “Ebb”, and wouldn’t remember to correct. I could maybe have solved this with initial prompt – either “you are a music teacher” or “always pronounce sharp and flat correctly”.

Overall this launching from “please quiz me on chords for different keys”** was very impressive.

This part later when I put my phone on the table and left the room was a little unsettling. Apparently the sound of my door closing said “This is Deokyoung Lee from MBC News” in Korean.

 

 

*Enabled in beta features of app.

**actual initial prompt: “Can you quiz me on notes in piano chords in different keys? Either the key name and I’ll name the notes.”

 

Change the flag

The licensing was unclear on Wikipedia but you know the flag that I mean:

used by Alan Bond in the 1983 America’s Cup and by the Australian Olympic Committee for the 2000 Olympic Games.

The Union Jack obviously needs to go and more people recognise kangaroos than the Southern Cross.  Just imagine our cool cartoon roo amongst all the boring stars, stripes, crescents, etc

get intents for google recorder

trying to find a way to automate google recorder using Tasker. Prompt suggested using Intents.

helpful stackoverflow gave abd command to run.

windows computer has recentish adb installed, doesn’t have grep, so this part fails.

| fgrep -i intent

remove that and list everything to a file, we can find relevant bits later.

Ended up finding something for stopping recording, but not for starting
10-07 21:07:59.900 31231 31231 I Recorder_RecordViewMode: Recording is ending
10-07 21:07:59.901 31231 31231 I Recorder_RecordingEngin: Scheduling stopRecording

Top GTLDs 2023

  1. .com
  2. .org
  3. .io/.co/.net
  4. .ai/.xyz
  5. .dog/.lol/.wtf

Top = my favourite. GTLD = generic top level domain. Best for digital product and services and/or if you sell to multiple countries.

  • No, no, you’re right. You’re smarter than Paul Graham, Jeff Bezos, Elon and Zuck. Low renewal fees, a namesake stock market bubble and trillions of dollars of value created 😉
  • Wikipedia lifts .org above every other alt TLD. Usage is situational but there are plenty of businesses where it makes sense, see Craigslist and AdBlock Plus. I also have a soft spot for it because I flipped superfungames.org for a cool $500 when I was a young buck
  • .co’s biggest strength is also its biggest weakness; its similarity to .com. You will leak more traffic and emails but if users actually make it to your site then it might seem more familiar
  • .io has existential issues and renewals are a ripoff but tech bros love it
  • .net seems dated but renewals are reasonable and it is still familiar to a lot of users. Your average small business is probably better served with a .net than a .co (less leakage and renewals cost half as much)
  • .ai renewals are obscene and I doubt it has staying power
  • Cheap registrations led .xyz to being abused by spammers and scammers
  • I’m joking about .dog but honestly if you’re not using .com you may as well
  • I have seen .lol and .wtf do well on Hacker News

Will LLMs worsen link rot?

Link rot is bad enough already, probably going to get worse if “sources” are added automatically.

Example Conversation

“Comparing Animal Strengths in Relation to Humans” linked to “Influence of the Hohenwarte reservoir on tilt and strain observations at Moxa”
“Human vs. Animal Physical Capabilities” was a 404 on oxford academic.

Since it’s prone to hallucinating external information, there seems to be a tendency to either get links wrong, or make them up entirely. In some non-web-enabled ones it would claim to read a link provided, and tries to guess the content based on link text.

Generate app implementation details with ChatGPT

Conversation

My first question was far too general, so got me some generic unhelpful answers.

Asking for 20 ideas (inspired by Brainstorming section from this talk) and  including specifics got better specific answers.

Conversation helps refine requirements. In this case I wanted to think of some different possible interfaces, and maybe technology suggestions for a specific part of it.