

But if they don’t ever get access to the internet, they can collect all the data they want? Unless they connect to nearby unsecured wifi and use that to connect to their server.
Two tired mice in a pail of milk, They swam around as best they could. But hope began to fade - what should they do? One wanted to drown itself, But its friend said, "No, no, no, For hope only triumphs, maybe, As long as we keep searching for it. Keep searching for it.


But if they don’t ever get access to the internet, they can collect all the data they want? Unless they connect to nearby unsecured wifi and use that to connect to their server.


Aren’t all TVs non-smart if you do not connect it to the internet?
Oh no, this picture reminds me a lot about myself…


A friend of my worked at a company where they had metrics on Claude code usage and some employees just started multiple agents on the same project where one was tasked to implement a feature and the other was tasked to remove that same feature…


But isn’t codeberg only for OSS? I imagine most companies won’t be able to migrate to codeberg for that reason.


I actually hadn’t thought about it until now, but I used to get texts from recruiters all the time, but that stopped completely in December.


I just read the update list. You can have an AI assistant answer your incoming calls and have the AI questioning the caller who they are and why they have called… I will hang up immediately if the phone is answered by AI. Such a weird feature.


This one is even better




The 257 spike is 2021


No, but their bosses might be.


What I like about, I think, is the private assistance feature, but I can achieve that with other solutions, I wouldn’t need OpenClaw for that. But I don’t think I will go that way anytime soon. I think it will stress me too much.
I am using AI for development daily. I describe an issue or feature to an agent via a skill and it returns a set of tasks in a structured and validated json format, then I run that json file through a python project I have created, looping through each task one at a time, and then I have my python code to structure how my agent is working. Each step is deterministic with short bursts of AI delulu, that again is validated against deterministic steps in pure python. It works quite good and each feature/task is approached in the exact same way where only the in between AI delulu deviates from previous runs, but it makes it much nicer, when you have something you trust in between what the AI is doing.


deleted by creator


Aren’t people horrified to give a hallucinatory program full access to your computer?
No, but should they? Yes.
It’s a privacy nightmare and the risk of something going wrong is quite high.
But, it is also a very interesting piece of software. I haven’t tried it out yet, and I am not sure I will, but I do get why people use it.


#yolo
Why even give an agent unrestricted access to anything critical in the first place? What do they think they achieve that they cannot achieve otherwise?


I have no experience with this, at all, but could creating symlinks from your internal SSD to your external HDD perhaps solve this issue?
Ooooohhhh…