crossroadsguy

Yes and this is what worries me.. the not yet part.

> AI doesn't yet improve on it's own

I mean when that day arrives and that aspect of AI is not controlled from now it will be quite unfortuante for most of the humanity (and let's just assume here we are not wiped out by AI; or not even mention that).

Think of nuclear technology. Is it smarter than us or something on those lines? the answer is it doens't matter. What matters is whoever weilds this power and then limited/restricted others (this was a good thing and a bad thing because some had – at the same time) from having that power essentially had a controlling upper hand on a whole lot of humanity.

AI is something like that with a big difference that it is essentially on the way to "replace" our usefulness, our professional relevance if I can say that. We can go about long spirals of "but soemthing else" will turn up, just like we can keep going about what if nuclear tech didn't even happen, wasn't invented, or what if it was done in such a controlled manner that only it's energy and other need was possible to harness (no pun intended!). It happened and this is how it happened. That's exacty what is happening with AI.

In the hands of few. Extremely powerful. Even if there are open models, running the bigger and better ones are simply out of reach for most companies (let alone people). And yes, it is already being weaponised. It's going to be such a weapon of control that nuclear tech won't even compare. Usign nukes to subdue a nation earlier meant also destrying a a lot of shared environment in the process. But with AI and almost exclsuive frontier level weaponised access to it with deployment capabiltiy the damage can be done is such controlled manner and scale that even things like protests will become too hard to do. In fact AI wiping out the humanity is least of my worries.

I couldn't help but notice something here. It is relevant with my writing experience/experiments with minimal assitance from LLMs (that lasted for 6–7 weeks).

> Greatness is a transitory experience. It is never consistent.

If you ever ask an LLM about these two sentences, it'd tell you that the second sentence is a mere repition of the first and quite possibly add that it "doesn't land". But that gives me hope. That there's something in those rules and algorithms manfiesting at the inhumane cost of unfathomable memory, disk space, and compute power that it will never (or for a very long time) match the human experience.

As little as I sought the help from LLMs (completely restricted to "in place" grammar and punctuation fixes and just flag it if it was not possible without sentence/phrase change) I noticed my writing was changing and not in a good way. It was not the insidiousness of these LLMs that was changing me but the nuanced incompetences.

So is OpenCode. They are quite a vendor.

I guess they will list anything from cash to crypto to bartering with or just using some sort of precious metal. Or quite possibly a more solemn "but do you need money at all?".

Yes. They know how to pitch an overhaul of your mouth. In fact if you get your mouth 300% overhauled at 3 dentists and go to the next within a month, you’ll be shown a package of how your mouth needs a complete overhaul. Or that’s how it’s here.

I don’t think it’s limited to dentists. The medical field is highly unethical and insensitive, contrary to what we are usually led to believe. Private hospitals here don’t even call you patients anymore, but “guests” and charge accordingly. The rooms are categorised like luxury, suites, even Maharaja suites.

This is my routine now when I sit in the chair:

Dentists: I am here just for the cleaning/scaling. I am aware of my reverse bite, crooked teeth, a wisdom tooth, a deep filling which may someday need RCT, and a tooth extracted when I was a child. I have no plans or intentions to do anything about these so please don’t inform me of any packages or plans regarding these.

Barbers: Just the haircut, no colouring, no spa, no facial, no treatment for growth or regrowth. Please don’t tell me any of that. I won’t do it.

Some still try and often I have to curtly cut them short.

1. It's very close to HDMI port (hint: backside of a TV isn't an area in hectares and kilometers)

2. Are we next going to discuss whether one of us has used the HDMI port or not? :)

And to answer you question: I used to insert a pendrive quite often to inspect Linux ISOs before I had FireTV on which I was able to install a general Linux ISO inspector app.

That's the accused speaking out loud after clearly noticing the newly installed spy camera: "Good god! Someone has put a recording device here. I would not have seen it had I not been feeling like dusting the back of this TV".

I mean, the last place you want to screw around with is a TV USB port. Anytime something goes wrong with the TV, those are probably the first places one would look. Maybe the second, if tapping and shaking didn’t work, that is.

Even the newer spy novels are lacklusture. We should have preserved Le Carré's and Greene's brains and make them keep writing. Or maybe I will just ask an LLM to do a Le Carré for me :)

> "when does FBI get involved in a case,"

Now I can see why local law enforcement would have made it a priority to get her :D

I started asking things I'd normally want no one to know about (but if they do, it's fine) in private browser windows, not logged in (duck.ai most of the time anyway), usually VPN toggled ON just for that. Now I just use an offline model for that but since RAM is the bottleneck on my mac so to even run a 6-7GB model I have to start aggressively killing anything and everthing that's running and then hope to clear up enough on this 16GB RAM machine. So I am thinking of hosting one on one of the oracle free tier instances (if I can somehow use that whole 24GB RAM, that used to be, at once – not sure that's available anymore). I tihnk Kaggle also offers something like that.

These kind of campaigns are just – find suckers who are willing to be our suckers. That too after they shtudown Safari for Windows and were never on Linux to begin with. And no, it's not fucking snappiest on the Mac either – even with all the special treatment it gets from the macOS (on iOS – there's literally no other option anyway, every browser essentially have to be Safari with none of the privileges Safari has). I think this company has become most the pathetic it can be. Utilised its full potential.

Though what stuck with me from that page is why the fuck they would have default browser setting inside something like "Desktop & Dock" (that combo!). That is just intellectually challenged UX/UI design.

And it seems they have fired everyone from their propaganda (or marketing?) dept.

tl;dr: Is Safari better than Chrome? Yes. How? Because this webpage is live.

If you have my-personal-domain.tld and you have 57 catch-all addresses then to send mail from them you have to add 57 email addresses in there. People know this “feature”. It’s just not what it is being discussed here.

You can enter any email address in that field:

any-user@any-domain.any-tld

Can be an alias, can be a catch-all email on your domain. Select the right email account (here, email account ≠ email address) with the right pre-configured credentials and that email will be sent, if not it will fail as it should.

It’s that simple and basic feature. But apparently email clients decided that’s not the right way and they make you pre-add every single bloody email address you ever want to use — this is specially painful for personal domains and catch-all addresses, especially the one-off ones.

Premium Lite is thrown in as well. I have AI Pro free for 18 months and I have checked the T&C docs.

I waiting for Pinbord to be shutdown or put in read only mode :)

If it has decent RAM and had it been cheaper, OpenAI alone will keep this product out of stock. This is Apple's love for the retail consumers that they were forced to increase the price just so that Sam would think twice before hoarding them.

I am almost certain that the only reason (feature) I have Thunderbird desktop installed has no place in this iOS app – an editable FROM field. I am pretty sure of that.

Ah, just saw the coolest thing - an epic subheading:

> Designed for growth

Love it. There's no stopping this app now. Godspeed, Mozila/Thunderbird! Grow is the new word.

I have seen this. Some devs actually write a pure swift ui app and still manage to make that look like anything but a pure switt ui app. Since the mothership is Mozilla I won't put is past them.

Yeah, did `killall Finder' quite a few times, just to be sure

Some apps just don't leave the dock.

> what I imagined as 'physical force'.

… and I "experienced" that (until class 7) – a lot. Became hostel prefect starting in class 8, so teachers were kinda scared of me after that. There were precedents for that though.

It (the "beating" kind) hasn't stopped in my country. Even in the cities, some parents look back on it nostalgically, and some, who are bigger morons, want it practised.

Danes calling their approach "physical force" feels like a personal attack and restrospective gaslighting :D

> hope the extension you find in the Pi extension store isn't an absolute dumpster fire

That's why I didn't mind it when Pi added native MCP capabilities. What dismayed me was they didn't other tools like subagents, and other stuff. I mean why do I have to scour the Interwebs to find something that doesn't possibly screw everything up for me.

I have a feeling harness usage will finally move to lots of harnesses with usage clusters - as in not X million harness for X million devs/users but a lot and people will use what suits them, and if not a more inclined coder will fork/make one just for them. In all their faults LLMs have made this a possibility.

What does it do? It sitll shows non-active apps. Unless I quit it and if I quit it then it goes out of dock even without this setting unless I've set "keep in dock" which keeps the icon in the dock even with this flag. Genuinely curious. Is it something more nuanced?

I stopped having any use of Dock other than seeing what windows/apps were still around that should have gone by now. But some apps keep toggling "keep in dock" for themselves so that makes it a bit more useless. Basically it shows what macOS has become – remove useful things, keep useless ones; repeat. There was a time aroound 2011-14 (or so) when this OS actually felt good coming from Linux distros. What worked for this company is the hardware competition esp. at fair prices just collapsed/vanished or at least severely lags behind.

Yes, Pi as well. All these harnesses have gone off kilter and are all for the LLM, by the LLM, and of the LLM at this point.

Maybe it's like online services/tools. Use them until they are VCed and gone pivoting and then move to another tool.

I was delaying it but one day Codex+GLM went ahead and did things in my ~/.dotfiles folder which I had granted only READ access for. I asked and I was given a reason which I didn't understand and didn't really want to. Right then I used sandbox-exec/safehouse (macOS) and tightened every harness installed (and the one not even installed, lest I install it later and forget to add/track them in the sb zsh init script).

But I am not satisfied. I am trying to find a really lightweight container/VM for macOS that eats very less RAM on its own and expands as needed. Because I really don't want to run an agent outside a container on my mac.

So is OpenCode. More so. I use Claude Code and OpenCode almost equally and Codex slightly less and Pi the least of them (not that it's worse, but because I use it for "non coding" purposes). They are all bad. Even this newer breed of "agent orchrestrating" tools.

One goes to Github and one notices, the dev is done by LLMs, issue triage is done by bots, and the commenting is done by the bots. (btw, the triage mostly means closing them or playing the "this is dupe of that" game while noone gives a flying fuck about any of the issues). Another good one is "not planned". You report a breaking/critical change and "not planned". What demorlised me is attitude of OpenCode devs/maintainers. I think the Open in it more of the "Open" in OpenAI than in FOSS. That's when I started reducing my dependency on this harness whihc was slowly becoming my pretty much full time harness.

Only if OSes have some easy and sanenly robust way of limiting app access in such a granular way that these apps might be as well forced to start behaving.

Like a simple:

- Dropbox:

    - Asked Permissions: File Access [{~/Dropbox, rw}]; App Install/Exec [/Applications/Dropbox.app]; Internet Access [*.dropbox.com]

    - They can have additional system defined accessible path inside ~/.cache, ~/.config etc and accessible only via their app package names (if they change their signature - not notarised or shit, user gets a notification and approves it) -> this is the tricky part. I'd rather have an app get a ~/.local/appdata/<app/package name> sort of blanket access for anciliary things and do whatever the shit you want do there.

    - optional permissions: []

 and so on… 

(also: the example given above is not fair game for nitpicking :D)

The thing is: the Internet access part one can control with Lulu or other similar apps. But anything else is a user nightmare - next to impossible even for a cli/tweaking/etc comfortable user. And mac's TCC is a royal mess - even their UI part for this is utterly confusing. I think only the Linux world can achieve something sane+easy like this (if it doesn't have that already; though they have not been known for being "easy").

I have achieved a lot of these for harnesses using sandbox-exec (by basically doing: "deny *; then selectively allow") on mac but it was a pain and I can't even think of trying something like that for "normal" apps.

That landing page is hard to look at, let alone read. Have LLMs really not yet learned to write webpages that read the sytem theme and look that way? Must be hard.

That's because calling an idiot an idiot plainly is apparently considered uncouth and attracts downvotes, flags and downvotes often mean oblivion. In fact you will find do-gooders chome in with "be civil" but you flip the word and it's all kosher. The thing is all of us do and say idiotic things. So that makes a bit tricky indeed.

> in the future being called a "genius" will always be seen as pejorative.

If you are not a genius and someone calls you a genius, well, for you the future is already here, genius! (Shit I didn't really mean that :P)