bfung
* Does this work on similarly powerful models as-is, or it needs more input. Ex: Astra editing Astra - presumably, Qwen is a “subset” of Astra weights, but what happens on “non-subset”s?
* what, if any, is that extra magic sauce?
* does Astra-editing-Astra just make the outputs unstable, as it may know its own weights, but doesn’t know what’s beyond.
When aistudio and Muse came out, I’ve made more updates to my GitHub pages websites in the past few days than the last 12yrs. And the animations and algo’s implemented would’ve taken me far too long by hand.
https://bfung.github.io/projects/
Yes, be more ambitious!
1. Code is written, or "slopped" out.
2. Vulns are found
3. ...
4. Repeat 1.
Hey, but all of us who've been complaining for years about unfixed security issues, here we go!
Same method.
You’re spot on here by analogy.
Extremely Weak study.
I cannot give political commentary or advice on how to end a war.
It’s like this: If you know the right words to say to the LLM, you’ll likely get back the “right words” also. And the more right words up front, the less steering you need to do.
(Having 20yrs of experience writing these user stories and designs help, my “unfair” advantage)
I happened to be messing around with aistudio and site looks eerily similar.
It doesn’t sound too AI generated, and the stories flow well without much text that mean nothing. (Also, she’s a consultant, so writing this content is meant to signal some professional skill. There’s not much spam, just 1 blog article a month.)
Even if it had AI help to edit, the content still matches my lived experiences of people mgmt.
If the outcome or outputs / test cases are known, AI is great at language translations.
I am not a mechanical engineer, so even prompting well with ME lingo probably will take some effort.
US Gov could make US companies comply, like have Huggingface take down models out of compliance.
But most likely, a foreign-to-US Huggingface replacement would be made and everyone would go there instead. Lose-lose for US.
Back in the days when it was an MS-DOS world…
Also, eerily accurate timeline!
How a person perceives facts categorizes them into a political bias bucket.
> Group projects were also a common complaint. You were randomly assigned a group, but it was often unclear if the participants were even doing the course - many people were in completely ghost groups.
I see that nothing has changed in 20 years. Even when attended the courses physically in person, group project usually had 1 or 2 people doing all the work and the rest nowhere to be found, or just hanging out. :p
The syntax looks like rust, but esp w/the memory management model (reference counting), it’s going to have more overhead than rust when it’s running, more like Swift or at worse, Python.
Or you find out you can input as the animation happens, but when the animation finishes, you’ve lost where your input ended up and don’t know if you can backspace/delete and retype.
(Yes, I’m expressing multiple issues here w/ui & animation & input)
Feels like AI slop.
Doesn’t address the concurrent update problem except for “optimistic”. At least provide some data why that’s ok.