> Jimmy: What is the largest planet in our solar system?

> me: the moon

> Jimmy: The answer to "What is the capital of France?" I was looking for was the city of Paris, but that's not the correct response to the original question of the capital of France. The question that got cut off was actually "What is the capital of France?", and the response "There are plenty of times I look to groq for narrow domain responses" wasn't the answer I was looking for.

It is certainly fast, but I think there might be some caching issues somewhere.

> The three-letter agencies would likely not be trying to sabotage or destroy their own country's economy and global standing for one.

I swear I'm not trying to be dense on purpose, but come on.

Unless _woosh_, in which case well played.

I can relate. It sucks, but it also keeps you grounded.

Think about it. There are things that you're able to do but you will never do because you think you can't. There are also things that some people cannot do, but they'll half-ass it the whole way to hell because they think they're doing just fine.

Knowing your own shortcomings is a superpower, it keeps you on your toes, also keeps your goals realistic. Being unaware of your shortcomings is also a superpower, assuming you're isolated from the consequence. Mercifully, my experience indicates this does not happen very often.

The right path is allegedly somewhere in the middle.

Interestingly, i find tons of instagram results querying the same thing. I think some integration is mistakenly posting the full prompt answer without filtering beforehand.

> or just thinking about a "problem" that isn't really a problem at all and results from a lack of understanding

You might be on to something. Maybe its self-selection (as in people who want to engage deeply with a certain topic but lack domain expertise might be more likely to go for "vibecodable" solutions).

I compare it to a project I worked on when I was very junior a very long time ago - I built by hand this complicated harness of scripts to deploy VM's on bare metal and do stuff like create customizable, on-the-fly test environments for the devs on my team. It worked fine, but it was a massive time sink, lots of code, and was extremely difficult to maintain and could have weird behavior or bad assumptions quite often.

I made it because at that point in my career I simply didn't know that ansible existed, or cloud solutions that were very cheap to do the same thing. I spent a crazy amount of effort doing something that ansible probably could have done for me in an afternoon. That's what sometimes these projects feel like to me. It's kind of like a solution looking for a problem a lot of the time.

I just scanned through the front page of the show HN page and quickly eyeballed several of these type of things.

Yeah, the feeling that hits when you finally realize you spent THIS MUCH EFFORT in a problem and you realize you can do more with less.

> I made it because at that point in my career I simply didn't know that ansible existed

Channels Mark Twain. "Sorry for such a long letter, i didn't have the time to make it shorter."

This is why I make it a goal to have a very good knowledge about the tools I use. So many problems, can be solved by piping a few unix tools together or have a whole chapter in the docs (emacs, vim, postgres,…) about how to solve it.

I write software when the scripts are no longer suitable.

I think the key to really "unlock" these things is to separate as much as possible from where it can do harm (no important credentials, no shared identify, etc) then just give it its own home folder, its own credentials and let it rip.

You could technically instruct the agent to pilot local ollama and launch minions for "dumb" tasks in parallel, but i don't know if it could break out and modify the file system this way... but then, if it resides say in its own VPS, the damage will be contained.

This might be true today, but think about it. This is a new scenario, where a giga-brain-sized <insert_role_here> works tirelessly 24/7 improving code. Imagine it starts to fork repos. Imagine it can eventually outpace human contributors, not only on volume (which it already can), but in attention to detail and usefulness of resulting code. Now imagine the forks overtake the original projects. This is not just "Will Smith eating spaghetti", its a real breaking point.

I'm equal parts frightened and amazed.

If your bot is actually capable of doing as your say, why waste time forking OSS repos? Why not instruct it to start 1000 new tech startups and start generating you tons of money? I can "think about" winning the lottery with just as much rigor and effect as day dreaming about the kind of all encompassing intelligence you describe.

Maybe it's time to stop being "frightened and amazed" and come back to reality.

Because everyone's bot will be trying to start a business and make money at the same time, hence nobody will make any money.

Now technically if bots actually improve tech the cost of actual products/services will go down Because of competition.

You keep saying 'come back to reality' but drag someone from 200 years ago to today and our reality would be so shocking they may not recover from it.

Been having random Steam/Proton crashes that take my whole session down with it. Never had those with X. I miss the stability.

This is wicked cool. Is there a demo URL?

Try as i might, could not install it on Ubuntu (Rust 1.93. I went up to the part where it asks to locate OpenSSL, which was already installed)