Can confirm this is a really excellent piece of OSS for local STT, I use it in both English and Dutch.

The only thing it has trouble with are brand/product/tooling/person names. You can add custom vocabulary, but then it tends to over-correct and insert those custom words when I never said them. However this isn't unique to local STT, frontier cloud models also struggle with this.

Hm, the main headache I have with .env files is simply that I lose them (switching between machines etc...), or the trouble of sharing secrets with team mates, etc... The headache of keeping them up to date and synced across environments & machines.

Not affiliated but those troubles are now finally solved with Infisical for me. It's open source so I happily give them a plug.

I feel like these days it's more like managing a team of seniors who are technically very competent, but may not always have the full domain context of the problem they're solving. And/or they forget parts, if that context is too large. And/or they have a poor temporal dimension (deprecated badly maintained information polluting the context).

They also tend to overengineer solutions if not guided well.

If you think about it, in that respect it's not that different from managing actual human senior engineers.

I think this is why focussing one's limited human attention more the input (defining clear requirements) as well as on validating the output (good CI/CD including end-to-end automated tests) is far more important than manual code reviews and micro-managing the development process.

What does "scanning" mean though?

Does this mean every parent has to now make sure not to take pictures of their children playing in bath for instance, in order not to trip these scans for false positives?

>in order not to trip these scans for false positives

They CLAIM they scan for CSAM, so watch out your documents and pictures with something that govt also wants to track.

For ages I've been looking for a way to easily share & sync a simple knowledgebase (HTML/MD and other files in folders) with my team (= including non-technical people), using Git as the sync/versioning layer, without it being too technical, and without getting vendor lock-in with expensive & unnecessarily complex cloud-based platforms.

Having built-in AI integration without relying on sketchy plugins would be the cherry on top (although, seriously missing the option to connect with any openai-compatible LLM provider like someone else mentioned here).

Seems like this might almost offer exactly that? I'll have to try it out...

That was our exact stated goal -- felt a lot of the same pain. Feel free to drop me any feedback here or @nickgomez on X.

> 10x more productive

That claim is totally worthless without you providing concrete information how you measured that.

And that's my point about value. That engineers can spit out far more code, or that they don't have to think much is surely precious convenience.

Value add so far lacks evidence.

Layoffs. It justifies them to the public. I'm not certain it grants them as it contradicts a principle of enterprise: scale, as much as you possibly can.

If tokens provided value today, we would be hiring more engineers to review their output and put things together.

I literally wrote how I measure this in the post you are replying to: #commits which is admittedly a worthless proxy for productivity, so, more importantly, number of finished production-ready features delivered.

That number is at least tenfold of what it was before, simply because I can run a lot of gruntwork in parallel now without wasting brainpower and focus on that stuff.

I created 5 websites this year and am working on 3 prototype games. For free. Without any knowledge of coding beforehand.

Value?

There are millions of other wanna be engineers doing exactly the same, assuming demand will scale as much as the offer.

What returns are you getting on those?

Let me create 500 websites, deployed for free, I hand that over to you by end of day. Will you give me a cent per piece? If so, happy to do business with you.

> luckily I don't have to. It's free.

Ponder that for a minute.

There are over 2 million games, for Android alone.

That you weren't making games before the advent of LLMs makes it cool for you to build, and at no cost. But people have been able to make games without them and already grew the market to saturation.

If the outcome of LLMs is that we get more games, it won't imply that people will consume more games. Most games never get played anyway.

There's nothing to "ponder" as you so patronizingly put it, and your stats on gaming are self-evident.

Op never said they're selling games. They said they're making their own games and websites for a fraction of the cost (even $0). That's amazing value. And it's just getting better.

that $0 is meant to go on the side of the value add that justifies the sort of funding we are seeing?

I didn't mean to patronize, sometimes self evidence isn't trivial to notice.

The funding is in anticipation of AI becoming so good that mistakes are only seen in the most complex output. In consumer applications, it's hard not to see that happening, given the exponential improvements of the past year. Whoever gets there first can capture the market.

Isn't this just an artifact of their chain-of-thought reasoning? If they are verbose in their output, it's more likely the next word predicted is actually correct.

Also, I see this more as a feature than a bug. In many projects I inherited in the past, I wish the original devs were a bit more verbose. Then again, with every developer using LLMs now, probably the opposite applies now.

You could also use plain markdown files, any free Markdown editor/IDE, and git, and sync with a remote Git repo using gcrypt for encryption (git-remote-gcrypt).

It's just a bit of a pain to set up, and also, not mobile-friendly.

yeah, that's the whole point! :D

The 2% of cases when you need the commit log (or more importantly: someone else who inherits your code...) justifies writing good messages imho.

If you make a change to your codebase, normally you know what you want to achieve and why (otherwise... what are you even doing?). A commit message is just putting that in writing... that only takes a few seconds, often less than it takes to write the code.

So it's just a good habit to have. It forces you to think more about the changes you do & why, so it makes you a better software developer. Creating any new habit always takes some energy initially, but it's worth it.

You know prisoners dilemma - if we even never meet at all it makes even more sense for me to cut the corners.

If we work together for years it makes sense to cooperate.

Unfortunately most IT projects are set up in a way where you do it for 2 years and then you will never ever work on it again.

Cool, but I wonder... is this really a feasible workflow?

The way I use LLMs is, I enter a very specific query, and then I check the output, meticulously reviewing both the visual output and the code before I proceed. Component by component, piece by piece.

Otherwise, if you just "let it rip", I find that errors compound, and what you get isn't reliable, isn't what you intended, increases technical debt, or is just straight up dangerous.

So how can you do this from a smartphone? Don't you need your editor, and a way to run your code to review it carefully, before you can provide further input to Claude Code? Basically, how can you iterate from a phone?