Hacker Newsnew | past | comments | ask | show | jobs | submit | blueberrychpstx's commentslogin

Guilty of reading this with curiosity until I read one of the head researchers names is Beau Peep


Mandatory shoutout to Scrimba here that does this for online tutorials that are purely JavaScript based (IIRC)


Haven’t clicked so fast on anything in a while. Excited to use this on desktop


That’s a hilarious over assumption but point taken

Also I really enjoyed your analysis


Reminds me of trying to read Gullivers Travels


You might be thinking of some other literary work; Gulliver's Travels isn't known for being particularly hard to read.

Myself, I was reminded of Finnegans Wake by James Joyce.


Emailed and it bounced. Is there an alternate address we could send your our info?

We're writing to let you know that the group you tried to contact (team) may not exist, or you may not have permission to post messages to the group. A few more details on why you weren't able to post:

* You might have spelled or formatted the group name incorrectly. * The owner of the group may have removed this group. * You may need to join the group before receiving permission to post. * This group may not be open to posting.

If you have questions related to this or any other Google Group, visit the Help Center at https://support.google.com/a/lava.xyz/bin/topic.py?topic=258....

Thanks,

lava.xyz admins


I'll just hop in here without reading the article and say that I've actually been using UML (plantUML specifically if that matters) to communicate with LLMs about software structure with some pretty good success.

Turns out computers are good at dealing with symbols, who knew!?


Is this satire?


Sadly, this is the attitude of some obese people...


First of all, I'm not obese. Second, you lack reading comprehension. Third, you come across as a judgmental and unpleasant person.

It's obviously possible to lose weight with diet and exercise.

It is completely useless (scientifically) for a doctor to say, "Go exercise and lose weight." Same for other similar things, like weight loss and nutrition education. It's been proven over and over again in scientific literature that it doesn't affect outcomes at scale, every trial shows the same thing.

People know that they should eat less and exercise, saying it is not the issue.


Pot - Kettle on that.

For a non-scientific case study of 2 - I know one obese person who has had gastric surgery, and complication from it - it hasn't helped them, and one formally obese person who successfully lost 20kg and has kept it off. Consider perhaps that trial participants may in some sense be self-selected from the sector of the population for whom normal diets don't work.

fwiw... the latter person strongly recommended deleting all sugar from the diet.


"First of all, I'm not obese. Second, you lack reading comprehension. Third, you come across as a judgmental and unpleasant person."

I never said you were obese, I said this is the attitude of some obese people. Not the same thing, so maybe reading comprehension is something you need a little bit of help with.

Judgmental? Probably a little...As someone who lost over 100lbs and has kept it off for over a decade the old fashioned way...exercise and portion control...hearing people make excuses for why they cannot do the same gets kind of lame after a while.


It is the attitude of most people who have tried to lose significant weight (tens of kg).

Note that I personally don't think surgery or semaglutides are a great solution, since they still don't attack or even try to identify the roots of the issue.


I mean, it only is because most people either don't have other options or don't care.

Us HN nerds could easily build alternatives we just don't. Or the ones that we do are so niche we never find them.

Interesting how there always seems to exist this dialectic


> The main challenge in UI design is balancing between: - Allowing the user to perform desired operations in as few steps as possible

- Without cluttering the screen with all kinds of irrelevant controls

Interestingly, I just watched a video by David Khourshid (founder of stately.ai; xstate/state chart/state machine fame) on how LLMs can interface with state charts of your application logic to find the shortest path to accomplishing a goal.

It doesn't seem like too far of a stretch, if your application is designed to support this use case, that an LLM can convert intent to shortest path for a user. I'm very excited about the possibilities here personally.

https://www.youtube.com/watch?v=qoNDyOClTtI


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: