Well, huge shoutout to you for following up on your word!

https://gitlab.gnome.org/rickyb/network-manager-applet/-/com...

Ashamed to admit that the power of monetary motivation got the best of me here. But it was also nice to apply myself.

Update: The PR was merged upstream and I'll pay out the full bounty.

Thank you very much!

Now Linux is a good amount better on the desktop.

If you’re against anthropomorphism of LLMs then how can it “encourage” you if you’re not having a conversation? How could it “convince” you of anything or cast something in a bad light without conversing?

Your point about censorship, however, I fully agree with.

> If you’re against anthropomorphism of LLMs then how can it “encourage” you if you’re not having a conversation?

Humans are more than biased word predictors.

That has nothing to do with the guy who said stop anthropomorphizing llms and then proceeded to anthropomorphize an llm.

Do you have any good starting points? For example, if someone had an ollama or lm studio daemon running where would they go from that point?

That functionality may exist, but I’m learning it from this comment. That is very nonintuitive and hard to discover.

And how is YouTube becoming better? Because in recent years if they detect ad blocking on a network? They will shadow ban the entire network. I can no longer use YouTube without a VPN because every single video cuts at the 1:00 mark. No explanation, no pop up. The videos simply load indefinitely. I have tried numerous solutions, but when I’m on my home network? I either VPN or I don’t get YouTube access.

This has been my situation for at least 2 years across multiple devices and accounts.

This might be the first time I’ve seen someone happy about an advertisement in the wild. It is a cool video though!

The ads for ReMarkable 2 and Apple’s Don’t Blink are quite captivating and entertaining in a way that I can’t claim about typical advertising.

I’m not sure where you’re pulling “backdoored” from, but if Apple markets their devices as private then it seems reasonable that end users expect a private device.

There's probably not a backdoor in the device. At least I haven't seen any news about that. But.

Apple has been an NSA PRISM-partner since 2012: https://en.wikipedia.org/wiki/PRISM#/media/File:Prism_slide_...

Also, apparently they had 100% success rate installing malware on the devices: https://www.forbes.com/sites/erikkain/2013/12/30/the-nsa-rep...

It's been close to 12 years since Snowden. Who knows how the defense has improved. Who knows how the offense has improved.

> if Apple markets their devices as private then it seems reasonable

Not really.

> if Apple markets their devices as private then it seems reasonable

So they are people reading hackernews who really think that marketing is honest and good faith?

Yes, the "care" about our privacy. That’s what they wrote. It must be true then…

It can be brute forced if that’s what you mean. It has a fairly low difficulty curve and these old games have a grid system for movement and action selections. That’s why they’re pointing out the lower parameter amount and CPU. The point I took away is doing more with less.

It definitely cannot be beaten using random inputs. It doesn't even get out of Pallet Town after billions of steps. We tested...

Based on the other examples of random inputs not being sufficient, I dare say the fish-based attempt may have been fraudulent.

dyor we only tested it with a pufferfish, courtesy of puffer.ai / pufferlib RL library. i promise it doesn't work with random inputs.

I'm not sure if you're just making a play on words, but I believe the commenter was talking about the streamer who sets up their fishtank to map to inputs and then let's their fish "play games". They beat pokemon sapphire supposedly. https://www.polygon.com/2020/11/9/21556590/fish-pokemon-sapp...

The prompt explicitly says “not Rust”. So the answers don’t say Rust.

Claude’s web UI has some strange limitations. You may be better off using another provider that just uses Claude 3.5 Sonnet API. One example of many is Kagi’s interface. You can set a system prompt and Claude will actually follow it instead of trying to be too clever. If your prompt says “give full and complete code files at all times unless specified otherwise by the user” it tends to follow that way more accurately than Claude.ai. May be worth a try for you to check out some other providers/interfaces.

Perhaps...

Seems more like throwing good money after bad as they appear to make it so you have to get an API key to do anything useful and then there's the possibility of spending significantly more than the $20 month 'pro' plan. Not something I'm really all that interested in considering this has nothing more than entertainment value and, from a video on the youtubes that broke the costs down, they have the highest per token rate.

I have enough yaks to shave to justify $20/month but anything over that...

I’ve had really good luck building micro-SaaS up to a certain point of complexity, and beyond what a coding assistant will do.

A lot of the problems you describe are due to the need to provide adequate context, project details, and rules in your prompt.

Claude will generate files it doesn’t think already exist, and in a SaaS project, you have many files.

Claude will struggle with syntax and proper usage of library/module/package versions beyond its training data. You have to provide your project with knowledge to work around this.

Lastly you will hit usage limits while working on projects because it’s a fixed cost offering. You can track and generate a project status to pass on to the next agent. This works “ok” and when I hit my sonnet limit I use haiku to bug and type fixes.

Bottom line, an out of the box chatbot is a great playground to flush out your techniques, but most software projects have complexities which must be managed in a separate system designed to manage all the details and break down the project into hundreds or thousands of individual tasks.

I want this magic wand too, but you have to build that yourself (or buy it when it becomes available). It’s been a fascinating learning process.

The problem is I'm not doing anything as complicated as what you're describing.

The task was/is to take a grammar for APL from some long forgotten paper and turn it into a lemon parser. Easy, peasy, well within its wheelhouse and it had spectacular initial results with the help of DeepSeek-R1 analyzing its work.

"Oh, good job, robot," me types, "let's work on a lexer. Hmm... you seem to have clipped out some important rules at some point, we need to add those back." Then, boom, Claude is completely worthless.

I want Claude to succeed. It was doing so well then it hit a self-reinforcing wall of failure that it just can't get over even though it can analyze its behavior and say exactly why it keeps failing.

I mean, exactly zero people think the world needs an APL interpreter written by the robots but the point of the project is to see how far they can get without having a human write a single line of code. I know they have limitations and have no problem helping them work around them.

But, alas, this project is shelved until the next big hype cycle.