There are quite a few comments here talking about how comparing images from feb/march isn’t useful. Here’s data on what’s going on. This snowtel location is within the Utah picture in the article.
Where can I find similar data for the Columbia River basin? That's where we're going to see large impacts on hydropower production come mid-to-late summer, I suspect. Impacts for the PNW and CA.
I've been vibe-coding a Plex music player app for MacOS and iOS. (I don't like PlexAmp) I've got to the point where they are the apps I use for listening to music. But they are really just in an alpha/beta state and I'm having a pretty hard time getting past that. The last few weeks have felt like I'm playing wack-a-mole with bugs and issues. It's definitely not at the point others will be willing to use it as their daily app. I'm having to decide now if I keep wanting to put time into it. The vibe-coding isn't as fun when you're just fixing bugs.
Genuinely curious: are you actually vibe coding (as in not writing or looking at the code) or are you pair programming with a current model (eg. Sonnet or Opus) using plan -> agent -> debug loops in something like Cursor?
I think it's great that you've gotten back into coding, even if you're hands-off for the time being.
However, I strongly urge you to leave not touching the code behind as a silly self-inflicted constraint. It is pretty much guaranteed to only get you to about 40% of the way there for anything more than a quick prototype.
Hardcore cyclists can confidently ride without touching their handlebars, but nobody is talking about getting their handlebars removed. It's just a goofy thing that you might try for a few seconds now and then on a lark.
This has been exactly my experience too. I switched from Spotify to Plex, but discovered there really isn't a music focused desktop player. So I vibe coded one, exactly how I want my music player to work (albums not playlists/tracks as the central item). I was so happy with my desktop app, I built a mobile version to use instead of PlexAmp. There are some bugs I'm ironing out, but they are both I've stopped using PlexAmp and Spotify entirely.
I very much like the no LLM output in communication. Nothing is worse than getting huge body of text the sender clearly hasn't even read. Then you either have to ignore it or spend 15 minutes explaining why their text isn't even relevant to the conversation.
Sort of related, Plex doesn't have a desktop music app, and the PlexAmp iOS app is good but meh. So I spent the weekend vibe coding my own Plex music apps (macOS and iOs), and I have been absolutely blown away at what I was able to make. I'm sure code quality is terrible, and I'm not sure if a human would be able to jump in there and do anything, but they are already the apps I'm using day-to-day for music.
I often give ChatGPT simple tasks and it gets them wrong. Yesterday I took a picture of a video game and told it I was stuck, only to be given instructions that lead down a bad path in-game.
I also often retest new models with tasks old models failed, and see some improvements. I really liked “format this SQL generated by my ORM and explain it” last week.
I honestly have no insight on if the tasks it is failing to do are right around the corner or if they are decades away.
Great question - similarly, I've seen posts recently (Fly.io's comes to mind) where people are talking about how "swarms of AI agents are using our service".
I'd love to learn more about what that actually means - does that mean tool usage from LLMs? Cursor agentic mode? Command-line hints for how to do a deploy?
We're entering an era where PR/the press is talking a lot about "AI agents" and I'm not sure that fully matches with the reality of what's going on out there en masse (at the moment).
I would if I didn't think people on the selling side were paying to get in my shopping basket. In that case, it feels like it would be too easy to get ripped off. Knowing how the world works that is exactly what will happen.
Me: "Chuck and Lisa are coming over tonight with the kids. Find me a recipe for dinner they'll all like and have the ingredients delivered in time for me to make it. Remind me to turn on the pellet grill if we're using it."
It: "It looks like it's going to be a beautiful afternoon. How about reverse seared tri-tip? There's a sale at FoodMerchant..."
This is a deceptively difficult problem. Food is incredibly messy -- grocery delivery is very far from being a solved problem even with a human in the loop. You have to deal with stockouts and sensible replacements, and driver/picker error, and quality variance. Quality variance is a huge issue in perishable categories and a major reason why foodtech is tremendously difficult (and fun, IMO).
Simple quality variance examples: banana ripeness. Or size of items that can only be ordered by each instead of by lb. Or one of the two onions you needed looking mostly fine on the outside but rotten on the inside.
As an experiment, try ordering all the ingredients to make a specific recipe several days in a row. You'll tend to hit an failure rate between 15-30%. That failure rate is usually fine if you're just restocking for home -- you can always pick up milk/sugar/whatever tomorrow -- but it's pretty awful if it means that something like 1 in 5 of your dinner plans are ruined or you have to leave your guests to rush to the store to pick up some missing ingredient
Also: the LLM will need to be aware of your home inventory, unless you're fine with it ordering lots ingredients you already have
So there's lots of hidden complexity here. If they turn this on, it will be a fun party trick that will work once in a while, but getting burned with ruined plans causes people to churn out fast.
all you've done is outline a series of mildly tricky but completely solvable problems to a use case that most humans would find incredibly useful. its very strange that you cant extrapolate 5 years down the line and see that this is completely reasonable.
Underestimation of the problem space is why foodtech is a tarpit for tech companies. Many have tried and failed to solve these very problems over decades. I don't blame you, to a green outsider the food industry seems like it would be simple, but the devil is in the details. I'd love for you to prove me wrong though
None of this is to say that LLMs have nothing to offer here. There would still be value in being able to tell an agent "Here's my list, get this ordered for me". But being able to say "find me a recipe for dinner that my guests will like and have the ingredients delivered in time for me to make it" without getting burned every other time is actually a much harder problem.
I tend to agree with you overall. Think about a small case study with avocados; what’s the confidence level you could order 3 avocados that you need to use for a recipe upon delivery and that you’d be satisfied with the quality and ripeness level? I’d put it at probably 20%, which means it’s a non-starter.
Literally tonight I ordered heavy whipping cream, strawberries, and biscuits from Doordash's dashmart store to make strawberry shortcakes, having forgotten about this thread. Until I saw the whipping cream was puffy and expired nearly a month ago. Haha
10lbs of ribs ordered at the pickup only bbq shop an hour away. 20 gallons of coleslaw ordered from another place delivered to your old address. It sent an improper command to your smoker which is now targeting 900F for the next 20 hours. Perfect for your party of eight people.
Don't get me wrong, I truly agree there will probably be a point things will be an agentic future. The same chain of events could have been said about booking travel arrangements a couple of decades ago. But until the rest of meatspace actually moves towards those things being normal these things are still in the realm of fantasy on average.
Did I give a number? I just said "until the rest of meatspace actually moves towards those things being normal". Is that next year? 5 years? A decade? More? I don't know. But it's not going to be normal tomorrow, I'm pretty certain of that.
I realize you probably wrote that yourself, but that apology is way too short. You're also missing the context where the previous recommendation was the same sourdough.
Buying, absolutely not. But I could see a use case of describing your requirements to a product in natural language and it searches matching products and finds places to get them. So using the AI for the thing it's good at: transforming natural language. And not for what it's bad at: making reliable decisions.
I use AI to explain brand options in spaces I'm not well versed in (for example, I don't really know how to trust Home Depot's positioning of certain brands, and I just don't trust their store purchasing teams as much as I trust Costcos or Targets). It does OK. It gives me a list that I can branch out and Google from.
I had two friends give their credit cards to ai agents nearly a year ago and were flabbergasted that anyone else in the group wasn’t immediately hyped to adopt the technology, much less have a problem with it
Pizza and shit on Amazon from what I recall. They had some belief that any mistakes “would be fixed” with no further explanation or really ability to even respond to further questioning on who would be doing the fixing, why they would be fixing a mistake caused by someone else’s complete lack of fear of risks, or how that “fix” would mechanically function
Yes, I use LLMs to help me buy gifts for friends. It works really well. You type in their personality and interests and a price range and you get several good ideas.
Maybe a naive question but I don't really understand the why of this? Why do I need ChatGPT in Apple Intelligence? Shouldn't Apple Intelligence just do what it's asked? Is that Apple saying it's Apple Intelligence isn't that good? Is this some business dealings I don't understand?
It sort of parallels setting a default browser on your phone. Do you want to use Safari or Chrome? Do you want to use Apple Intelligence or OpenAI? But that's really not what it is, because everything is still funneled through Apple, then to OpenAI.
my understand is that apple intelligence aims to be a tiny model that runs locally, and when it identifies that a request is complex it sends it off to chatgpt
though it looks like this is just the first of many 'extensions' that can be added to apple intelligence
I think this problem is even worse than just ghost jobs.
My partner is currently looking for a new job. Two or three times now, they’ve completed the whole interview process, gotten great feedback. Then they are ghosted for 2-3 weeks and the company comes back and says “sorry we decided not to hire for this role”. It’s utterly exhausting.
I do think when the interviews started, they had intentions to hire. (My partner knew people at the company and was recommended). But then for whatever reason during the hiring process, the job goes away.
- Racial, gender, and/or local citizen discrimination avoidance
- Job security for HR so they themselves don't get laid off
- Over-interview to exceed capacity/ERP needs
- Market and/or competition intelligence
Perhaps it behooves jobseekers to stop looking for scant, temporary, insecure, disloyal, abusive work and create or sell goods or services through collective, employee-owned co-ops instead.
https://www.cbrfc.noaa.gov/dbdata/station/swegraph/swegraph_...
reply