plutokras
plutokras on Hacker News
What if Hacker News had topical sub-HNs so people could post things that aren't Hacker or News? (:
I was skipping Tahoe too after seeing all those posts about the differently rounded corners.
This time I took the plunge and upgraded, and I have to admit the whole system, especially Safari is much more snappy than before.
AFAIK Brave Search is also using its own index.
> It feels quite slow
It definitely is. The extension-based redirect in Safari is also unreliable. Furthermore, many of my searches (and others', apparently) unexplainably defaulted to Groningen in the Netherlands, even though I'm nowhere near the place.
I ended up not renewing my annual subscription. Since then, I vibecoded a small userscript that replicates domain ranking for DuckDuckGo – plus DDG already lets you turn off ads natively.
I remember them advertising Svelte as the framework that disappears in build time.
The SimpleUI plugin helps a lot with the clunkiness.
> Eventually, this arms race ends with a computer vision model that looks at the screen, classifies visual elements as ads, and draws a rectangle over anything that looks like an ad.
That would be a killer feature for AR glasses. Imagine no billboards, no political posters, no neon storefront clutter.
This feels like obvious setup for regulatory capture. It won't be long before missing "safety" watermarks are cited as the pretext for restricting Chinese models.
What specific technical signals make you think we're close to a shift like that?
> My friend didn’t have the vocabulary to ask the AI to write code
I had the exact same realization using Claude Design. It’s great that "anyone can design" now, but I don't have the domain knowledge to describe what a good design consists of. I know it when I see it, but that is far from enough.
With the recent wave of posts about Claude rewriting entire codebases from Zig/Electron to Rust/Swift, I can't help but question the prompter's actual confidence in the final result. Gaining a thorough understanding of the generated output still demands an enormous amount of effort. I suspect the reality is that most people just chain a few review agents together, and if they output "LGTM", the code gets committed and pushed.
I have been doing daily agentic coding myself since last November, but lately Im having concerns. We are on the verge of becoming Warhammer 40k Tech-Priests: chanting sacred prompts to appease the machine spirit, praying for a good result. The foundational knowledge is lost, meaning that even if we do look at the code, we won't understand it anyway.
> I personally like the ability to filter my own results by promoting, demoting or blocking certain domains to filter lower quality results further.
I had an annual Kagi subscription that I let lapse not long ago. That was hands-down the best feature, so I vibecoded a small userscript that replicates it for DuckDuckGo. DDG also lets you turn off ads.
I'd gladly return once they fix the integration issues. In Safari, the redirect via the extension is a bit wonky at times.
What's the unique value proposition here? I checked it out and seems like yet another Chromium fork with some privacy added on top.
Applying an ostrich policy to Chinese models won't make their underlying geopolitics disappear.
Much of China's innovation is state-funded specifically to compete with Western counterparts and erode their margins. By open-sourcing these models, China applies pressure on the US ecosystem.
You enjoying free/cheap access to high quality models is the intended effect of that strategy.
Can confirm. Traveling via public transport in Switzerland is remarkably uneventful. It's a stark contrast to my Eastern European home country, where it is a gamble due to a certain demographic's anti-social behavior.
Enterprises would do anything to develop on Linux except using an actual Linux distro.
I'm happy to report that this game is very fun for natural intelligence entities too. :)
I see Claude's frontend skill is the new bootstrap.
My annual Kagi subscription lapsed last week, so I decided to see how DuckDuckGo is doing these days.
The feature I missed most from Kagi was domain filtering, so I had Claude write a quick userscript for DDG that lets me boost, pin, and block specific domains. uBlock Origin aside, DDG even lets you turn off ads natively.
Kagi is good, but the redirection felt a bit flaky lately, and I was dealing with an annoying bug where my localization kept defaulting to Groningen for no apparent reason.
I’ll stick with this DIY setup for a bit, though I might well end up back on Kagi once I realize how good I had it.
Last time I looked into it, I realized how severely it's limited by memory bandwidth. Only the M5 Ultra compares to a dedicated graphics card, but it still falls short.
This is my exact plan too, if I ever have to leave the Apple ecosystem.
At my company, devs were the ones pushing for the Claude subscription. Left to management, we would have only had GitHub Copilot – we already have an existing relationship with them and the tool is good enough.
If Anthropic is intent on losing the goodwill of the devs, they might not be happy with the consequences. Their product is quite commoditized at this point – the latest GPT, Gemini or GLM is just as good for most enterprise tasks.
They tick all the boxes I care about – desktop & mobile app, cli – but for the same price I might as well just go for the leading providers.
We are in a thread about hamburger tops...
Git wins by not needing to be replaced badly enough. Latley you can just ask an agent to "amend the last commit" so even that is being abstracted away.
I do hope the rare earth metal in my calculator is also ethically sourced.
In high school I kept a USB drive full of portable apps. This was one of them. I can still recommend it.
They can train on the outputs i.e. distillation attacks.