6 whole months?! Gee golly thanks mister!

Agreed. Seems like it should be indefinite given they created a multi billion dollar company off the backs of these maintainers dedicating their hard earned timed for free to begin with and then trained models against their code.

IMO this is an insult if anything

Especially considering they trained the damn thing on our code.

Do you complain to the bank that credit cards have expiration dates or to the government that passports also do?

The bank mails me a new one automatically.

Could we be heading towards a world where it's just more secure to write inhouse software again, only now with AI agents? Not closed source per se, but 'own source'?

Seems cheaper (and so far more robust) to have an agent audit downloaded code

It's more likely we will move to a world where desktop OSs have a security model like ios/android so malicious software can't steal your data.

The endgame is to generate a binary image for an entire single-purpose OS/unikernel that does exactly and only what you require of it. No source to open or close.

The build process is just as vulnerable.

Sounds more midgame.

I remember 15 years ago when our Minister of Foreign affairs was gleefully telling a gadget-vlogger about his personal setup where he was not using 'official email', but his own private Blackberry / iPhone (I forgot) and email for communicating all things. Out of 'frustration with how long it took for official IT to get things sorted'. Video is still online even: https://vimeo.com/13224190

Let's not exchange crap behaviour. I think google would win hands down. Firefox at least has adblocking.

The classic 'those guys did something bad, so I am going to go with the guys who are absolute assholes doing several orders of magnitude more bad things now instead' response.

That usually means that whoever utters it was just looking for a sycophantic excuse to go with the bigger threat because it is more convenient to them (for now).

It's remarkable how often this happens, isn't it? One incident of someone not living up to standards is suddenly an opportunity to abandon standards and go with known bad actors. It's like people giving up on the MSM and immediately latching onto propaganda Youtubers instead.

People latch onto consistency and hypocrisy as their filters.

The problem is that anyone trying to actually be better is usually inconsistent and hypocritical at some level as in that "you criticize society, yet you participate in it" comic.

If you attempt to filter out all traces of hypocrisy from your trusted sources, you wind up listening to the absolute worst people.

The people trying to do better are usually the ones struggling with conflicts and inconsistencies.

Let's be real. People love their shiny big brands, and will find any tiny excuse to keep using them.

Other way around isn't it? Google are the worst assholes for the time being so many as well go with the less bad assholes?

Maybe "wicked problem" is the new tech buzzword, but browsers certainly are one, and Mozilla messed it up. I blame Mitchell Baker for a big chunk. We don't need a new browser though. We need a new web.

https://en.wikipedia.org/wiki/Wicked_problem

Not at all. Firefox is a trap to keep motivated people from banding together to create a real user-respecting alternative.

As a user at least I have an option to use ublock origin extension in Firefox. So I'm somewhat grateful I can still browse the net peacefully and safely.

That's exactly my point: You and many others accept a local optimum.

No it doesn't. Unlike Brave, Firefox needs an extension to block ads just like Chrome.

Yes, though it has the most powerful and customizable adblocker available.

Yet it is not in the submission. How am I to know you all assume male sporting events?

Passable and fine is the Hallmark of capitalism.

Nice! I do this now locally with LLMS and ollama and my own havky prompts. I could not find if this also supports ollama?

Thanks for checking it out! ollama wasn't top of my list for support, just because I don't have a machine powerful enough to run decent local LLMs (I wish I did!). I'll look into it though, nothing here should be locked in to any one LLM, as long as it has the concept of a skill/slash command/reusable prompt.

Someone else asked about Gemini, so I think broader LLM support will be my focus for v0.4.0

I'm sure this is true. Also true is the mental distress I experience having to work in an crazy noisy open office space. Give me an actual office, and I'll go there.

An actual office is not even that expensive. All they have to do is double the height of the cubicle walls and slap a door on there but they won’t do it.

I'll settle if they double the height so my eyes don't get blasted by sun glare.

There's beautiful views from my current office..but my job is a screen all day and having dim interior lighting versus direct sun fighting it out across my retinas means the effect is entirely lost on me.

It is all about control and bad leaders do not know how to lead without doing “drive bys.”

> Personally, I don't know a place more hyped up about AI than HN.

Other than every boardroom on earth you mean? ;-)

I use AI daily. But not with agents. Those feel like cars before there were safety measures, like seatbelts. I'm no anti AI. I'm just waiting for the seatbelts.