Perhaps they disagree with the idea that it’s an addiction or that it’s a problem with screens in particular, rather than a problem with people not being able to or not knowing how to spend their free time in other ways.
If you stare at a wall all day because you have nothing to do, are you addicted to staring at the wall, or do you just have nothing to do?
If someone stops drinking for a long enough period, with no urge to return to drinking, then yes, they aren't an alcoholic. You just made up a silly 12 hour window so you could beat a straw man to death.
If an alcoholic has been clean for decades, he is still an alcoholic, because the second he takes alcohol again, his brain switches back to addiction mode. That's the thing with addictions, they even destroy the good feeling you initially had about with drug.
When you are staring at a wall all day, you can probably think of a lot of other things you could do and did. When you stare at a wall all day, and think of nothing and enjoy it, then I would say you have mental problems. The problem isn't that you do something for a long time, the problem is that you can't think of something else or can't control you to do something else, even if you want.
I can see that, but IMO the main difference is that this feels like it's intentionally trying to be an active detriment to your life. TV et. al are fairly neutral generally. Even with the ads.
But with targeted advertisement, it feels a lot more like they're trying to get inside your mind to steal your money.
And with content on social media, it feels specifically engineered to make your life as bad as possible. More fear, more anger, more racism, more sexism. Here's some big boobies, now look at this disgusting immigrant. Isnt Earth awful? Aren't these guys ruining everything?
This. Targeted adds + bespoke algorithms make our current tech incomparable to the previous boogeyman of TV et al. We have devices that are designed to keep and farm our attention at all costs
Asking here because it seems related: I'm trying to use cursor to work on a webapp. It gets frustrating because vanilla Cursor is "coding blind" and can't actually see the result of what it is doing, and whether or not it works.
I ask it to fix something. It claims to know what the problem is, changes the code, and then claims it's fixed. I open app, and it's still broken. I have to continuously and way to often repeatedly tell it what it broken.
Now, supposing I'm "vibe coding" and don't really care about the obvious fact that the AI doesn't actually know what it is doing, it's still frustrating that I have to be in the loop just to provide very basic information like that.
Are there any agentic coding setups that allow the agent to interact with the app it's working on to check if it actually works?
You can use things like Browser Use and Playwright to hook things like that up, but you’re right, this is a very underdeveloped area. Armin Ronacher has a talk that covers some of this, such as unifying console.log, server logs, SQL, etc. to feed back to the LLM.
Look into the Playwright MCP server, it allows coding agents to scrutinize the results of their work in the web browser. There is also an MCP server for the Chrome DevTools protocol AFAIK but I haven't tried it.
I was in the same boat on a side project (Electron, Claude Code) -- I considered Playwright but ended up building a simple, focused API instead that allows Claude to connect to the app to inspect logs (main console + browser console), query internal app data + state, and execute arbitrary JS.
It's sped up debugging a lot since I can just give it instructions like "found a bug that does XYZ, I think it's a problem with functionABC(); connect to app, click these four buttons in this order, examine the internal state, then trace through the code to figure out what's going wrong and present a solution"
I was pretty resistant at first of delegating debugging blindly like that, but it's made the workflow pretty smooth to where I can occasionally just open the app, run through it as a human user and take notes on bugs and flow issues that I find, log them with steps to reproduce, then give Claude a list of bugs to noodle on while I'm focusing on stuff LLMs are terrible at (design, UI, frontend work, etc)
I don't know if plywright works without chrome in debug mode, but I tried the MCP for chrome devtools and it requires chrome to be started in debugging mode and that basically means you cant log into a lot of sites (especially google) since it will block you with an "Unsafe" message. Works pretty well if you owe the target website.
a built-in mcp server that takes a look at what's broken and communicates with cursor is on our roadmap. Join discord and we will keep you posted there.
So actually I have this setup (of a bridge server) which I use for agent4 itself (so claude code can talk to agent4), It makes a lot of sense to publish that bridge as well in the MCP form.
I was rather explicit about that, you memorize them from trusted sources (or directly observe them). There's no question. It's just a fact that it's not something you can bootstrap from a computer that doesn't know them.
And as the person up thread pointed out, the LLMs are in the middle of destroying many of the trustworthy sources by poisoning the internet with a firehose of falsehoods.
Just because "they" tried that and it didn't work, doesn't mean doing something of that nature will never work.
Plenty of things we now take for granted did not work in their original iterations. The reason they work today is because there were scientists and engineers who were willing to persevere in finding a solution despite them apparently not working.
I didn't even notice the text in the image at first...
This isn't even about resizing, it's just about text in images becoming part of the prompt and a lack of visibility about what instruction the agent is following.
While I also did not see the hidden message in the image, the concept of gerrymandering the color at higher resolutions nearest neighbor to actually render different content at different resolutions is a more sophisticated attack than simply hiding barely text in the image.
There's two levels of attack going on here. The model obeying text stored into an image is bad enough, but they found a way to hide the text so it's not visible to the user. As a result even if you're savvy and know your VLM/LLM is going to obey text in an image, you would look at this image and go 'seems safe to send to my agent'.
// Optimize special case if (x == y) return 1; else return x/y;
reply