jwpapi

Thank you guys. I learned something new.

Damn that page took down my Chromebook, never happened before..

In the chart they use "Pareto Line", which I think is wrong. Pareto is 20% effort leading to 80% results. Which could be interpreted as models costing 20% having 80% of peak intelligence, but that’s not what it looks like to me.

It looks like the "Frontier Line" to me, which is also often misinterpreted. frontier does not mean the best models. It means all models that are not strictly dominated, meaning in most cases: Not same price or cheaper and more intelligent.

I personally would like the word frontier to be used with more criterias: Open Weights, per use-case, etc etc. This would make model selection easier, but I understand it’s not an easy thing to do.

How about runpod

and economically viable

I think it can make a lot of sense to make a set with jev and then train laya on that set and do the rest with laya for saving $

Okay I understand.. he’s up for the internet fame.

With everybody bashing OP here, how is he supposed to even make money ? It’s n open-source model you self-host right? So he doesnt seem to be just greedy? He might genuinely feel like stolen. I hope he doesnt take the comments personally and is able to find motivation in it.

I’ve tried it versus Jev and I got significantly worse decisions. I hosted it on runpod nvidia t4.

I wanted to classify business b2b vs b2c and business model. Am I holding it wrong?

Jev says you should restate state in the question and I tried it:

{ "decision": { "type": "noul", "instructions": "Is the rolled number in state odd?" }, "question": { "type": "noul", "instructions": "Is the number odd?" }, "question-3": { "type": "noul", "instructions": "a 6 sided dice rolled a 3 Is the number odd?" }, "question-4": { "type": "noul", "instructions": "a 6 sided dice rolled a 3 Is the rolled number odd?" } }

=>

decision,0.168,0.83 question,0.141,0.86 question-3,0.029,0.97 question-4,0.021,0.98

so im confused too..

A weakness with numbers?

Where can I subscribe to a hosted version of this? I don’t want to host my own GPU.

I’m missing an actual explanation of how that works.

I feel like we all had the idea, but how is all possible move sequences proven ?

What if the possible scenarios are too big to proof or test.

Like on a 2 dimensional game it’s easy, but you could make it multidimensional and introduce an unlimited amount of special rules, (if on a prime number dimension on 3 but not more prime numbers you are allowed to jump to another prime numbers with 3 but not less coordinates)

How is bend protecting it? I was checkin github and the paper, but I was not motivated enough. I feel like an actual explanation of how proofing works is missing.

For Lean I understand how it works, here not.

It’s classifying faster and cheaper. A lot of immediate ideas are better solved by pre-classifying + embedding, but their doom example or the wikipedia runs are one where you can’t preclassify.

In Jetbrains I do secondary shortcuts and I name them as what they are in my hand:

Alt M + V = Move Alt E + C = Extract Component Alt S + E = Search Everywhere _ many more.

Or just vim combos.. with ideavim

You just have to do it so often that you’re annoyed by it and then you learn the shortcut and then you force yourself to always do the shortcut.

May I ask why you ended up there instead of just using the heavy subsidized subscription. I’m actually curious.

I think first of all it’s not an obvious idea, also the marketing surplus for other providers is not as big for openai/anthropic as for xiaomi and last but not least I’m pretty sure you can withdraw methodology from here.

I’m saying who has a million dollars for me, so I can make my own model?

I’ve played with it already. I don’t think this is the use case. I think Jev’s use case is fast, cheap and somewhat easy classification. It’s not trainable in the way you would want here. Even though it’s fast it wont be faster than pgs query optimizer.

At least as I understand things.

How did you plan to use Jev for query optimization?

I don’t know that’s why I’m happy to discuss.

When I have a clean codebase it’s super powerful and faster than I am. Then I start to use it more, more sessions and longer tasks less checking in between.

It kind of works but later I’m in a deadlock where every change introduces new bugs or takes ages. This might be for a lot of reasons for example me going to fast, me losing mental model, me explaining it wrongly.

However when I then start checking the code it’s all spaghetti like frankly the spaghetti Astra produces I’ve never seen before. Processes that should be simple stretch over 11 files with weird wrappers and abstractions and I need a whole day to entangle it.

These are ai assisted user workflows that Im working on in this case.

I just have the feeling no matter what AI just always expands it. And expansions hinders agility and sometimes you need that.

I thought that the new models were super smart. Fable and Astra. They definitely outperformed their previous generations, but after a couple of weeks of heavy usage my codebase again is a stupid mess and there is no way out except me fixing code by hand.

My new suspicion is now that they didn’t got drastically smarter, but they got trained on the user input on the previous generations. I don’t think anymore we had a massive intelligence jump. It just seems like they know more edge cases. Therefore I see this as marketing.

Happy to discuss.

Yeah that was what I was most worried about when I read the top comment here. I found the use of language a feature not a bug. I don’t care how good it reads. If I can communicate with it concicely it’s enough to get my work done. I don’t hate the language for copy either, but yeah different users, different problems.

Venting reduces the likelihood of acting in aggressive feelings

But a lot of the research is not about 'loneliness' in particular, but rather how friends or social circles make you happier

I know the difference, but the studies I’ve heard of seemed to rather focus on the benefits of social circles, not analyzing 'loneliness' in itself. However I haven’t fully digged into all the evidence, but I hope you guy’s are right!

All these studies suggest loneliness makes you unhappy, however I feel happiest most when lonely and doing my thing and not with people. With people I just feel frustrated or weird, because I think so different than the others.

First of all that could be a causality ≠ correlation, but more importantly. Even if it might be the biggest predictor, it might not be the biggest lever.

Still interesting train of thought that I might need, but the article is exaggerating the evidence and not adding the right disclaimers.

Fair point.

I still think you could build single person cars that are more secure than traditional cars and use less space and energy

I’m thinking that since 2015. Like BMW C1 just with doors on the side and a bit more security. This would approx allow 3-4x as many travellers on a given route compared to traditional cars.

Terminology is a crazy lever with AI

I think for small projects you need to scale the coders mental model, which afaik works in the fastest time, when you let ai do the exploration and planning, but coder needs to write the code itself and then ai verifies. That generates the best of world codes and the coder at least has written the code. It’s scalable.

In projects that are so big that no single coder or no small group of coders is sufficient to grasp I don’t have personal experience, but my guess would be that they are just a cluster of other small projects.