Unfortunately there are like a billion competitors to this right now (including Playwright MCP, Playwright CLI, the new baked-in Playwright feature in Codex /experimental, Claude Code for Chrome...) and I can never quite decide if or when I should try to switch. I'm still just using the ordinary Playwright MCP server in both Codex and Claude Code, for the time being.
I would use whatever you are comfortable with, I wanted a similar tool so I coded my own. Smaller API so that understand what is going on and it is easy not to get lost
It's insufferable, yes. Even though I'm a left-liberal, it feels foreign to me. Twitter is worse at the limit (endless neo-Nazis and Maoists) but at least I feel some diversity while I'm there. Bluesky is so uniform in the annoyingness of its community.
I used to feel like you do, but I don't agree. I would just say it is not consistent. For a given codebase and given goal, sometimes Claude will be the more sensible, creative, thoughtful planner and sometimes Codex will be, sometimes Claude will make a serious oversight that Codex catches and sometimes the opposite. But the trend for me and seemingly a lot of people is that Claude is a more "human-like/human-smart" planner than Codex (in a positive way) but is more likely to make mistakes or forget details when implementing major codebase changes.
Correct, this is the way. A year or two ago lots of people were saying to do the opposite, but at least now and probably also even then, this is better. Claude is a more sensible and holistic designer, planner, debater, and idea generator. Codex is better at actually correctly implementing any large codebase change in a single pass.
tmux makes it easy for terminal based agents to talk to each other, while also letting you see output and jump into the conversation on either side. It’s a natural fit.
This applies to basically every military and company in every country in all of human history. Nearly every single other country tries to spy on every single other country, including on the US. That's just how these things go.
I think a lot of the younger generation supports it, actually. They didn't really grow up with a culture of internet anonymity and some degree of privacy.
The younger generation is growing up where the internet is a giant dumpster fire of enshitification that a tanker full of gasoline just got poured on in the form of AI chatbots. With agents becoming even easier the equivalent of script kiddies are going to make it so much worse.
Privacy with respect to the government was one of the final pillars, but when everything placed on the internet is absorbed by the alphabets of government agencies, and the current admin does searches of it as their leisure they understand nothing is anonymous anymore.
It's funny that this is what the younger generation is going to think Millennials and older are completely stupid for still supporting. The current structure only benefits corporations and bots.
We need to destroy privacy and anonymity online for the noble goal of the government banning teenagers from looking at Twitter and Instagram?
If it's a concern, parents can prevent or limit their children's use. If all this were being done to prevent consistent successful terrorist attacks in the US with tens of thousands of annual casualties, I'd say okay maybe there is an unavoidable trade-off that must be made here, but this is so absurd.
"Preserving privacy and anonymity online" is not an inherent good. It depends on how it is being used and what the consequences on society are.
Thus far, privacy and anonymity have been used to get children addicted to garbage, distribute CSAM, create elaborate schemes of financial fraud (cryptocurrency), and develop drug distribution networks.
It's completely reasonable to limit privacy in order to combat these social evils.
It isn’t just about teenagers though I think I outlined that? We need to make sure people online are real people and yes we should prevent kids from being exposed to algorithms designed to addict then.
Adults are nearly as susceptible to such addiction. If this is the goal then the actual legislation should be to prohibit social media companies from doing it to anyone. (I think this would be government overreach and a possible first amendment violation, though. I say this as a center-left person who deeply hates what Musk has done to Twitter. I would even describe myself as an anti-free speech person; I just respect the nation's laws and the principle that the state should not be able to imprison you just for speech.)
reply