teekert

Later on you can hover over the image, and the tooltip will pop up the address. It will be a great resource for contacting interesting people! /s

Care should age? At what rate, do you propose?

I a way yes, it is their duty to their future happiness to explore. No doubt some will not word it like that, but I met some that really do (and I envy them, I was indeed a bit mind/clue-less).

Teenagers would experiment a lot less with sex and drugs, if that was the requirement ;)

(Or what would we call the thing the teenagers do?)

Yeah, this is similar to how it went with me. I must say I wasn't too precise because I was in planning mode anyway, but it sort of blamed me "Yes I did that despite planning mode ... To be fair you did say..." for saying something like "let's go with it" (which for me meant removing planning mode then stating exact instructions). So planning mode is not "Only construct a plan.md without execute permissions", I guess we both witnessed what a "soft-guardrail" is.

Ah yes people get into trouble in all sorts of ways.

We went through this right? This happened at the beginning of the year (https://news.ycombinator.com/item?id=47150122, probably more links on HN). It's a super careless thing to take such tech and just release it on anything important, and she's a "security researcher" no less.

This is just a competitor with an agenda (pro regulation) trying to scare people away from unregulated stuff.

Yesterday Claude Code made 5 large edits to my codebase in planning mode (claims it used a bash script instead of standard read/write tools so the guardrails didn't trigger) it's why I put agents in containers.

In this case the "disastrous failure" is even from a super careless "experiment" by a "competitor" that likes regulation.

Fwiw, I call that experimenting.

You can check the scripts and cronjobs, als ask it to summarize the scripts actions (using another agent/model if you want). All in all, LLMs are not 100% trustworthy but generally things go as intended.

There are reasons to be careful indeed, but for me all instructions were followed nicely so far.

Yesterday I had Claude (in CC) do a large number of changes to my codebase using a bash script, even though I was in planning mode and in claude.md it says: Always first list the steps you're going to take before execution. It apologized of course... But I know how LLMs can be. I take that into account.

For me the problems are always when I pull some image (like GitLab) and try to get it to work with podman. Or the hoops you have to jump through with podman-compose (user lingering, systemd services, privileged ports (80,443) [yeah I know it's a feature]). Docker just works, Podman (I feel) still requires stuff that makes it less declarative (to get to a running infra).

Still, having a gitlab runner with a docker in docker setup that can access the host docker socket is not something you do lighty, so I am eyeballing buildah etc.

I guess what really grinds my gears is that I'd use podman a looooot more if it could nicely coexist with Docker. I'd use Docker for the big services and podman for all my own stuff. But that is just not possible (at least not afaik), so it is also difficult to switch step by step (yes VMs, bla bla, but it's all complicating).

Imho it say something about you that you see people that experiment with new things as "mindless people". I'll go search for my mind now, thanx.

Yeah that's true, and in many cases the AI just sets up a cronjob and a script (and a mailbox, and an interface to telegram, and a reporting structure). But it's nice that in case of errors it handles the edge cases or it fixes the scripts. It can give the crontable over telegram, you can pause it for the holiday "Number one, pause all processing until further notice"...

But sure, it's not "rocket science", in fact, the skills to set it up indeed would probably help you set up the same scripts. It's just behind a chat interface.

It can be nice to say: "Add another minecraft world with the same user whitelist on port 25566" or "create a demo website for a home battery on domain claw.xxx.com". But it is indeed not very useful for me yet. I think the more access you give it, the more it can be like a PA, but I don't want it in my calendar/home assistant/paperless-ngx etc... yet... When I even get to this point I can see it being like my secretary ("Please get my incomes taxes statement from 2024", "Estimate this years income taxes from my invoices so far", "Plan appointment with ..." etc)

I think this is a good question, as with any of these new things you don't really feel any need indeed.

My claw scrapes some APIs, receives some emails with job listings, and matches it all to my profile. It can also fill two folders at 2 domains with anything (ie a demo for a website). It can also receive emails, make PFDs out of them and forward them to my bookkeeping software (which can only deal with attachments, not emails.) That last thing is just a script. I use Agentmail btw (a ycombinator startup), was easy to set up.

2nd iteration I was indeed eyeballing Hermes which is supposed to be more structured, maybe claw2 also is... I want to add some things, like have it manage my son's minecraft worlds (using docker compose), maybe have it access a calendar so it can make appointments (not sure how to set that up in a useful way yet).

The thing is in a Hetzner VM far away from anything important, dealing only with public data (except for the occasional invoice).

It brings the requirement for a firewall on every endpoint with a unique address. My Phone often has an ipv6 address (found out this holiday wen I couldn't resolve one of sites because of an orphan ipv6 entry nobody noticed), and has little problems. Perhaps there is also "firewalling" on the router and the phone can't even have incoming connections. Not sure. In any case, the phone seems to do fine.

Imo they could have sold it like that, in this case. A warning would be in order though.

Do you know about docker compose overwriting your carefully set firewall rules? That’s the other docker thing…

Oh man I will never let them read my private comms. So what are they going to do to me? I’m afraid that I, as a good person and father, am going to be punished for not letting them read my private messages. I’m afraid for my future in the EU.

It’s that age old “start a docker container with the docker socket in the container and you are effectively root”. What are we talking about here? This is not new?

But, this “vulnerability” is the thing everybody knows about docker since forever. I always make my user part of the docker group, so my NixOS also has this, and any Ubuntu I’ve used over the past year. What is different here?

Start a docker container with the docker socket mounted in the container and now you can have yourself mount / as rw. Everybody knows this. How is everybody so shocked here. Many instructions online tell you to make yourself part of the docker group for convenience (like the digital ocean one).

Us kind souls are not forced to listen, however, something in our nature draws us to these extremes, and then, observing a lot of these extremes, our minds label them as “common”. It’s all quite unsurprising when put like this, imho.

The antidote is real interactions, and ignoring the online extremes.

I watched the announcement on the detection on gravitational waves on YT. The comments scrolling by were like from another world, I even made some screenshots, insane, obnoxious. Could be bots I suppose, I hear from political commentators here who advocate for thoughtful commentary "from the middle", that their social media posts are always very quickly flooded by the same kind of polarizing low-level comments that drown out any intellectual and thoughtful debate. It's probably partly bots, partly a small minority of people that get sucked into it by the bots. I have no problem believing this is Russia, or NK, undermining our democracy in a fully automated fashion.

Yeah, I just came back from traveling a couple of weeks, and I have had such wonderful experiences with people. There were times where I just wanted to hug a taxi cab driver (ie when a Grab driver was holding an umbrella over my vomiting daughter [car sickness] and me, with his car stopped by at the side of a highway... etc.)

Meh, it doesn't really look into corners ahead, it should perhaps be more warped on the sides. Smart idea though.

I think the opposite. The vast majority of kind and gently people are suddenly observing a small but ultra loud obnoxious minority take the stage and burn resources like nothing else to get maximum attention. Attention wins and you don’t get it by being gentle, balanced, kind and most importantly, don’t care about maximum attention.

Not sure. It didn’t do “cat” so I guess that the file itself did’t leave the computer? Uploading all files in my ~/ would have taken noticible time and didn’t happen I think.

I once opened Zed, howdy there was an agent window on the side, I log into Claude. I asked it to list what it could see and work with... And there my (priv) ssh keys come scrolling by. I don't know what I was expecting really, it's very logical, but also very in your face. They didn't leave my computer I guess, I just showed me the output of some `ls` commands. But still.

So now I have CC in a container, mounting it's own credentials/memory folder per project and only mounting one repo at a time (script in the repo itself). I feel a bit better about it now. It can still access my networks of course.

"Some ventilation is still a good idea though."

I think a CO2 meter is an excellent idea, imho it is a good proxy for "air freshness", so also small particles etc. This year I want to try to ventilated more based on CO2 (so close the vents until CO2 becomes unacceptable) and monitor gas use (hooray for Home Assistant).

It wasn't that insane when our summer nights were 24 degrees C instead of 29, what a difference that makes.