Readit NewsIt was super slow (thought I think that applies to CLI Codex too), it wasn't outputting any text explaining what it was trying to achieve, and it started off down a path that made no sense. Claude Code in Zed has some rough edges but it's at least usable.
In terms of GUI agents, Cursor is still a lot nicer experience, IMO. Though I do still prefer just using Claude Code cli, personally.
Kudos to you for owning up to it.
As others have said, it's the kind of thing that could happen to anyone, unfortunately.
I generally recommend Google's to any Android users, since it suggests your saved password not only based on domain in Chrome browser, but also based on registered appID for native apps, to extend your point. I'm not sure if third party password managers do this, although perhaps it's possible for anti-monopoly reasons?
From the article:
>First, we are told, the relevant secretary of state (Michelle Donelan) expressed “concern” that the legislation might whack sites such as Amazon instead of Pornhub. In response, officials explained that the regulation in question was “not primarily aimed at … the protection of children”, but was about regulating “services that have a significant influence over public discourse”, a phrase that rather gives away the political thinking behind the act.
From the source (emphasis mine):
> On 18 March 2024, the Secretary of State was provided with a Submission which made it clear that Category 1 duties were not primarily aimed at pornographic content or the protection of children _(which were dealt with by other parts of the Act)_. Rather, the aim of Category 1 was to capture services that have a significant influence over public discourse. The submission offered, as a possible option, requesting information from Ofcom as to _how content recommender systems function on different types of service_.
The quote leaves out "which were dealt with by other parts of the Act" and the fact that the subject was specifically "Category 1 duties" not the Act in its entirety. It also doesn't mention that the subject was on content recommender systems.
_Again_ this is not a judgment on the Act itself, but providing the full context, which does change the message.
0: https://en.wikisource.org/wiki/Wikimedia_Foundation_v_Secret...
Meanwhile, Brits just look on at this narrative wondering what the hell they're talking about. Look, I'm against this legislation too, but if you actually live in the UK or even just consume mainstream British media, you'd soon realise that this narrative that's being pushed is a distortion that doesn't match day to day reality.
I only checked English, French, Dutch and German and assumed that Spanish would be OK. Was this for drag & drop. And do you maybe have the video? Maybe I need to tune the quality threshold specifically for Spanish videos.
I think it worked quite well, there's only about 10 headlines a day (out of 15k+) that get a significance rating higher than of 5.5 out of 10.
It also helps avoiding the overfocus on western issues and actually learn what's happening around the world.
Imagine you have an AI button. When you click it, the locally running LLM gets a copy of the web site in the context window, and you get to ask it a prompt, e.g. "summarize this".
Imagine the browser asks you at some point, whether you want to hear about new features. The buttons offered to you are "FUCK OFF AND NEVER, EVER BOTHER ME AGAIN", "Please show me a summary once a month", "Show timely, non-modal notifications at appropriate times".
Imagine you choose the second option, and at some point, it offers you a feature described as follows: "On search engine result pages and social media sites, use a local LLM to identify headlines, classify them as clickbait-or-not, and for clickbait headlines, automatically fetch the article in an incognito session, and add a small overlay with a non-clickbait version of the title". Would you enable it?
They basically already have this feature: https://support.mozilla.org/en-US/kb/use-link-previews-firef...