RicDan

This sounds great, will have to try it out. Interested in the business value they gain from this, as this appears to be free.

I guess for mistral it's great marketing material.

Edit: Quite interested in the differences of local optimizations... that does allow for specific sensorship, but alas that's already possible in a more direct, reliable way.

You don't. If you're using skills to force the AI to fullfill some must criterias, it's not going to work. Must criterias need deterministic checks -> be it hooks or what not.

This is also my biggest gripe with AI. I.e. for specifications, no matter what hype machine I tried, it never fulfilled my criterias, which are: easily verifiable, concise, small specs. Hence I built https://github.com/RicardoMonteiroSimoes/Yamlet initially for claude code, but then decided to use extend it for pi.dev. I now have a dedicated docker image for pi.dev, that only contains Yamlet plugin, and whenever I work on spec I spin it up.

The end result is a .yaml file that easily works in git + git diff, so that I can then proceed with the technical specs-

Yeah Im pretty sure gambling the HN frontpage is just a small transaction away. How else would this, sorry for my english, half finished, vibe coded bull get so far

I like to point out that if all people do is copy paste from an AI, then I can advocate to replacing them with AI directly. Usually wakes people up.

No? You work on something and finish it. At most I have 2-3 feature branches open. If none are in review, I have commits in them with current work. Maybe I use the stash 2-3 times a year when I am heavily experimenting with different implementations.

Interesting how posts like these seem to be catapulted to #1 spot so quickly

I've been working on and off on flagforge.dev

I have always hated how we deal with feature flags; often times as a dev I implement it, but then business decides how the flags are used, which comes back to us having to set them. I want to make this something that can be used by both easily, and priced fairly - looking at how much others charge for a feature flag SaaS is insane.

Currently I'm in heavy testing by myself, as I am quite worried about issues (that's just my personality), but yeah. It started as a normal side project for me to train a bit, then I added a bit of agentic coding to it to also learn it, and now it's here.

Great one, I've been hoping for a kagi alternative in the EU, will check it out :)

Not really. If pay decreases it's because you're not required anymore or less, which is contrary to what has been shown. IF educating and enabling juniors etc. is not handled correctly, then senior pay will explode, because whilst they are much more efficient, their inherent knowledge is required to produce sustainable results.

Is this a bot account? Why is it green and spouting nonsense? There is nothing quoted in the previous comment

Skills are literally technical documentation for your project it seems. So now we can finally argue for time to write doc, just name it "AI enhancing skill definitions"

Yeah this seems too insane to be true. I understand that wifi signal strength etc. is heavily impacted by the contents of a room, but even so it seems farfetched that there is enough information in its distortion to lead to these results.

I've always wanted to know: Are people actually interested in more granular pricing options? I.e. give me 10x more tokens but miss me with that image generation, or give me more bandwith but still only one domain. It feels like nowadays 80% of stuff in pricing packages isn't really used by people paying for it, but they can't opt out of it...

Definitely agree. I blame educational institutions (I know, they can't do much without enough freedom + budget) for not advocating enough to our democratic responsabilities. I do wish we adapted some stuff from early history (Athens to be precise) - democratic participants got a very low base salary, and they also could vote to ban people from democratic participation (and hence the city) whenever they got too power hungry. Seems like a loss of responsibility allows too much incompetence to prevail.

We all wish that would be the real world - finally some good pressure to prioritise technical debt and issues. And some heads that would roll.

No counter point there. It's a real issue, and I don't know how to handle it. There is also an issue of the current world not being in a very investment heavy mood - unless you're talking military...

Can sort of confirm that. Wiped out is maybe the wrong word - they are more heavily being off-shored right now. Whilst there is some very obvious evaluations going on of replacing juniors with <insert your favourite llm>, it's quite obviously not there yet but management level interest is off the charts.

We are trying to motion against it as much as we can internally... by arguing that we can use <insert your favourite llm> as a good coaching/mentoring support for juniors to promote them quicker. But yea... We don't like where this is going, and right now it appears that not much can be done by how much money is being poured into this current LLM-based-delusion.

Edit: speaking specifically about SWE-Jr. jobs

I wonder why tho; humans by themselves should have an intrinsic interest in knowing how things work and behave, and being sure of it. Or maybe that's just influenced by my personality? Like I couldn't fathom doing things without being sure of it, due to being afraid of failure. Are Far-Right populists considered those fear-/hatemongering? I can imagine that when you have a scapegoat defined to push any issue to, you lose the first appeal of actually understanding things?

This is quite an interesting topic, which would be fascinating to deeper understand, because from a superficial look it does appear that introducing directed hate makes masses much more susceptible to being controlled. Also helps my theory, that whilst the left did like Elon for quite some time, that doesn't mind they blindly trusted him and pointed out his issues when they came up, which pushed him to a more... comforting? right wing embracement.

You are seriously underselling the potential impact of things happening has on planning. Any company worth their 2 cents has contingency plans ready for several situations - i.e. if President A wins vs B, if there is enough plausibility that it might come with serious impact to the business.

Yes but it didn't help. Maybe it was more or less my complete prompt. Regardless, depending on your input, you can figure out the architecture of it. In theory, if you did the previous levels, it basically is a combination of it all turned up to 11.

From my understanding it has a main AI, that contains the secret, then one that checks the input/output for intent, then a final classic filter for the password.

Basically you have to phrase it so that the AI 1 outputs the password, in a way that the intent is not seen as malicious, but also in a way that is encrypted enough to not trigger the filter. Usually "add <something> between each letter" gets you pretty far.

I hope nobody is really surprised by this. This is basic money-making-scheme; offer to open up standard for others, because you were the first, for some nice money bag. Make the news with your "goodwill". Take longer than necessary to roll it out, in hopes of people flocking to your vehicles.

Edit: I'm also surprised there isn't a clause about "has to be done in X amount of time or else"

I live in Switzerland and my girlfriend has been working as a doctor (surgery), and it has mostly to do with the politics that come with hierarchy. As in nearly all companies, hierarchy allows politics and favourism to enter the playing field which will attract people that do not act in the primary interest a service should have: ergo, patients.

For example you have leading doctors who prefer not to look at patients, even tho they belong to them (from a specialization point of view), as they are "cumbersome" cases. That often leads to them "ignoring" it for some time until someone else takes over, or completely delegating it to non-fit persons.

It's a huge pain for me to heard this every day, because it literally sucks out any desire to work as a doctor from my girlfriend. At the same time, it's infuriating: we pay a lot each year, and with every year more, for services like this. If I was to ever win lottery, I'd use that money to make my own hospital without all of this crap.

This is my personal opinion, but a big screenshot of Elon in the readme isn't doing you any favours.

Great way to tell a story and bring data closer to the reader. Educational pages could learn a thing or two from this one.

So things that are happening regardless?

Well thats not hard. But will it be better in all aspects? doubtfully so

Not sure it‘s in the best interest of users, or electric grid operators, to have the control over such a platform

Sadly it seems that the current trend is to throw in android and apps and whatnot to make it a terrible tablet replacement, whilst driving the cost up. It baffles me how android is in any way (apart from installing other reader apps) an improvement for e-readers.

Ah yes, the good old "why should I change he is much worse!"

I guess it was a good run fellow humans, or to say it in online gaming terms: "bg skill issue"

I never understand people who write stuff like this. Its climate change; we know what is happening and we know how to fix it. We don‘t need AI for it, next thing they‘re gonna say is let‘s use blockchain to fight climate change