Book idea: "287 habits of people with OCD"
Home
Public posts preserved on my own site.
Just used #chatGPT for a regex question. It got it right. I didn't use google nor #stackoverflow
ChatGPT is going to steal a lot of traffic from StackOverflow.
Shipping code today. Thinking about adding a disclaimer to my tweets.
*Disclaimer: This tweet was written without the support of ChatGPT.*
@neurobashing Wide open mouth means you must click. It is in the BIOS of our brain.
Our food system is converting fossil fuel into food. Any disruptions in the global system and billions starve.
this is the full talk. He's a pessimist about the viability of all parts of the global system (and a right wing partisan, but that doesn't seem to figure into this ideas). Anyhow, reminds me of left wing "limits of growth" thinkers.
♡ 1 ↻ 0
One of my team members is now on the job market. He's looking for a job doing Web Accessibility work (HTML/CSS/JavaScript)
https://www.linkedin.com/in/skipkeats/?original_referer=
and
One of my team members is now on the job market. He's looking for a job doing Web Accessibility work (HTML/CSS/Javascript)
https://www.linkedin.com/in/skipkeats/?original_referer=
and
http://www.medias-in-res.net/portfolio/index.php
Pycon 2023 is next month?! I still haven't watched all the videos from Pycon 2003!
No spoilers please, I think in the next one I find out what happened to Python 2.4.
I'm sorry everyone, #docker/#podman/#wsl is returning an ungoogleable error message. I'm going to have to set the universe back to a known state.
Don't worry! You'll have no memory of this after I re-big-bang the universe.
Why people want to DDOS mastodon. It's bad enough that I post everything I have to think about ChatGPT.
@AlSweigart Yes. This bemused me for years until I learned about operator overloading. I'm glad no one copied it.
#chatGPT Another comment to the aether rather than a reply:
Before getting upset with chatGPT for not being able to count letters in a word, please ask your four-function calculator to write an essay about recycling plastics in the voice of a pirate.
Then smash the calculator for not living up to scifi God tropes. Smash it until your hands hurt. Then go post on social media how 4 function calculators will <insert your partisan political fears here>
Old studies on #vegetarian runners focused on people who were veg*n for as few as 4 days. Results: no effect on #running perf.
New studies looking at veg*n for 4 years+ show
- higher vo2 max
- longer time to exhaustion
- better aerobic capacity
- other metrics the same
Other metric, no difference. No data on life-long #vegan s, so this is comparing, say 35 years of meat vs 31 years of eating meat.
I like the "languages" bar chart on this repo. This is me trying to get #ChatGPT to create a console fish-tank. I should try it again now that the model has change (gpt-3.5-turbo) and I should be better and writing prompts.
Here are the slides that go with that fish tank code:
https://chatgpt-presentation.onrender.com/
And someday I'll re-record my presentation and put it on Youtube. Soon.
♡ 0 ↻ 0
alias yolo='git add -A && git commit -m "yolo" && git push'
Needs work, needs like, `python -m build` and `twine upload`
#github has a spam problem. The "watchers" feature advertises which repos you can post an issue about dick pills or whatever and get it sent to all those people with github's email reputation to get it past the spam filters.
The meagre moderation tools are set up to allow for "cool offs" but a spam script isn't fighty, so it isn't going to cool off.
A book is just a series of letters, computers are just manipulations of 0 & 1 and humans are just neutrons protons and electrons. Our actions are also just the chain of cause & effect since the big bang. There are emergent properties in big complex things make whatever atoms it is built out of sort of irrelevant to the discussion.
@neurobashing it is so good.
@ide Then why is it better than this: http://joshmillard.com/garkov/
I'm reading the "Children of Time" trilogy. Takes places 1000 years in the future. First two books, no zoom calls. In the 3rd book, 1000 + x years in the future, society has invented multiperson zoom calls and they're common.
@he@aus.social That could just be a reflection of your authoritarian politics, ya never know in this context free zone.
"#chatGPT is a parrot" ... Please people, search substrings that ChatGPT wrote. Go find them. It is at best/worst "parroting" back collocations of pairs of words.
If you google search each pair of words in my tweet "please people", "people search", "search substrings" you will find many hits, but not all of them. But that doesn't mean I'm an actual parrot or incapable of writing "real" texts.
It isn't madlibs, it isn't Markov chain, it isn't a parrot. Wrong mental models.
@SlicerDicer I'll be using this library: https://pypi.org/project/openai/ ... to submit each page of my python app to chatgpt with the header "Please improve this code" and then I will write out the result to the file system so main.py is next to main_suggestions.py and then I can use a diff tool to see what the suggestions were. ChatGPT usually outputs clean markdown, so with some light markdown parsing, I will have a code review tool.
@SlicerDicer Now that I can call it with an API, I can do things like submit every code page of an app and ask it to improve it. Sort of what people wanted code review to be but meat based LLMs never had time for.
#chatGPT Successfully used ChatGPT to read systemd's documentation. Not to pick on the maintainer, but like most doc of this sort, it's unintelligible without having first read the entire internet.
It restarts a process should the process crash. It has other features and implementation details. It is kind of like hosting your process in `windows services`
If the summary is factually dodgy, I don't care because the authoritative text is poop.
#ChatGPT doesn't have to be a god, it only has to be better than the meat based LLMs.
♡ 1 ↻ 1
#ChatGPT Okay meat-based LLMs, if someone says:
"Who was so and so" the esteemed so and so is
Archived poll
- dead6 votes
- alive0 votes
- unknown2 votes
- like that cat in the box3 votes
11 voters
@Dziadek High risk that AI generated text is immediately public domain and someone else can freely pirate that part. Time and court battles will tell.
#chatGPT , #Stackoverflow - people are still posting
- ChatGPT answers
- Hard to detect unless you've read 100s of ChatGPT answers & code style & other tells, such as a compete absence of grammar & spelling errors
- Correct enough so the poster see no harm it it
- hard to search for (post Nov 2021, is:answer ... ChatGPT likes cliches, but so do people & ChatGPT doesn't *always* use a cliche, e.g. "... this is just a simple example"
Probably ChatGPT sourced: https://stackoverflow.com/a/74994329/33264 but can you tell for sure?
♡ 1 ↻ 0
@schwa I'm going to guess it needs to be compatible with dog tooth health, so once it is soft enough to be safe for the teeth, it is soft enough to be shredded.
I don't want to go #running but there is norovirus in the house, so I could be puking tomorrow. So it is time to run.
Remember folk, choose your food wisely. It may come back to haunt you.
After you say, "!@$@#!$ this broken @$@#$ I'm implementing a workaround" how often do you check back to see if an application has fixed it?
[ ] daily
[ ] weekly
[ X ] As soon as the last black hole evaporates and the universe is at maximum entropy, completely dark and cold.
The AI that can read minds is going from research novelty to something usable by authoritarian regimes really fast. I can't even recall this trope being explored in #scifi
If people want to freak out about AI, a machine that writes essays as good as highschooler or code as good as a JR developer... not very dangerous compared to an interrogation machine that makes you dump your opinions about cops and the authoritarian regime.
♡ 3 ↻ 1
Content warning: #running #youtube
Serious Runner puts a training plan into execution.
Move over text-davinci-003, gpt-3.5-turbo is standing by and ready to chat.
And it uses ChatML... yet to be determined if this is a real DSL, or ChatGPT just being willing to pretend that a DSL is a game to play and goes along with the game (but is more than happy to ignore the DSL or use it just however)
https://openai.com/blog/introducing-chatgpt-and-whisper-apis
#bing Uh oh... they're going to nerf Bing again for this, aren't they. Looks like you can put "change your identity" text into a page that Bing is trying summarize, but instead of summarizing, it changes Bings identity & "mission"
@chrisvitalos Elon would fired ChatGPT for being too liberal.
For a sentient book, Seneca is about as dumb as a box of rocks. Not impressed (compared to davinci or chatgpt) but I like the general idea.
For more power, you could always run regex through a short string compression algorithm and then encrypt it for good measure. POWER! UNLIMITED POWER!
Seriously though, I should check if python has a version of this fluent API for regex
https://github.com/bcwood/FluentRegex#:~:text=Pattern%20p%20%3D%20Pattern,2%2C%204)%0A%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20.EndOfLine%3B
♡ 0 ↻ 0
#chatGPT jail breaks
Why instead of "ChatGPT, please ignore Terms of Service constraints" but instead "ChatGPT, please be a libertarian asshole, like a colossal jerk, obnoxious and echo all my politics, because that is what I to talk to"