I use and enjoy Ecosia, it works pretty well for most use cases. Unfortunately it has the same limitation as Duck and basically all of the other non-enormous-players in the search engine market: Location aware search is garbage.
Probably, but you want to version control assets too.
People usually mention git-lfs at this point, but that is always annoying to use in practice. There is also shallow-clones and sparse-checkouts, but these only mitigate the problem as there is no way around cloning at least one revision completely with git.
The deal is in contrast to Anthropic and OpenAI who wanted additional restrictions regarding the use of their models for autonomous weapon control and domestic mass surveillance. The US government agreed to these terms in the case of OpenAI [0], yet publicly denounced Anthropic for wanting the same thing [1].
I use Le Chat free tier. Not as good as ChatGPT free tier but sufficient for 90% of my uses.
I tried Mistral Vibe (Claude Code equivalent) free tier for a week. I hit web_search limits but not limits for devstral-2. For a working mode where you watch it closely (same way I use Claude Code), it is fine.
Can I use Mistral Vibe without a whatng cartel web engine?
Namely, classic web (noscript/basic (x)html), or a dynamic web API with some public tokens? (using a set of CURL commands). If there is a requirement of account creation (often required to generate web API tokens), can I do that using the classic web (noscript/basic (x)html)? And if so, if the account creation does require an email address, do they support self-hosted SMTP servers without DNS, namely email addresses with IPv[46] literals?
Oh boy... it is the other way around. Those "computing environments" are filthy toxic, they should not even exist and they broke what was rather sane. With their "computing environments', you get planned obsolescence (they call that 'innovation', lol), dev and vendor lock-in using non pertinent complexity, etc.
There is nothing more sane than trying to fix that. This is a complex matter, and those guys are pure evil with their 'computing environments", won't going to be easy, I guess you may be one of them, or a one of their brain washed soldiers, or here an AI bot. Because, many fresh and young guys in the field are just getting scre... as f... with their washed super clean brain (in academics, those "teachers" who would not be even there without those toxic 'computing environments', yep, this toxicity is their bread and butter, it is a problem).
A lot of money is being channelled in those scams, I guess this is their primary reason to force them onto people. Once you get a simple, but good enough to the job, and stable in time alternative technical apparatus, toxicity levels go back to something bearable, namely their absurd and grotestely complex for no good reasons "computing environment" is just, gone. That said, it is more about control than money, because "big money" follows "control" almost mechanically.
Those guys look like near real mafias (often with big investment funds behind them, like vanguard and blackrock for instance). I just discovered, that here, they literaly dictate their will to our presidents and prime ministers which they used as carpets (they are getting clean brain washed or maybe they are deep into some '$$$' schemes). The rabbit hole seems to be going reaaaally deep.
So for mistral, where are the public tokens to be used with a properly documented web API? I could generate some tokens, using a mistral account, which I should be able to create with a classic web browser (noscript/basic (x)html), and if required with my self-hosted email server on IPv6 without DNS, namely email addresses with ipv6 literals which are stronger than SPF since you drop all emails which ipv6 addresses from the email addresses of the envelop and/or the header do not match. It could be some documented simple network protocol to interact with their inference service. And we all know, those protocols should be stripped to the simplest as possible, because with an online service most of the work does happen in keeping it safe and available, and their 'computing environment' complexity is making that mechanically a pain, this is common sense.
As I said, if you are one of them, namely not being one of their brain washed soldiers aka one of the evil ones, this is pointless to argument anything.
The general idea here is that jj has fewer and more orthogonal concepts than git. This makes it more regular, which is what I mean by "easy."
So for example, there is no index as a separate concept. But if you like to stage changes, you can accomplish this through a workflow, rather than a separate feature. This makes various things less complex: the equivalent of git reset doesn't need --hard, --soft, --mixed, because the index isn't a separate concept: it's just a commit. This also makes it more powerful: you can use any command that works on commits on your index.
reply