Hacker Newsnew | past | comments | ask | show | jobs | submit | mrklol's commentslogin

Is there any reason to keep using postinstall scripts allowed instead of asking e.g. the user? Are they even needed in most cases?


If you ask the user "should I run this script" after installing, they will just hit yes every time. But also, a lot (I'm confident it's "most") of NPM install operations are done on a CI server, which need to run without human interaction.


I mean… putting the app onto the store costs a yearly fee + development costs. I don’t think the dev should pay that out of their own pocket.


I also don’t think our generation will see actual AGI, but imo the hard "intelligence“ part isn’t needed as we can use our intelligence. Using it as a tool will hopefully lead to plenty of cool things in the future.


Model says it’s only supporting English, seems like the demos on their page for other languages are using an older model as the quality is worse.

But the current one seems really good, tested it for quite a bit with multiple kind of inputs.


you could use it as an addition for e.g. chatting, emoting or whatever to look more like a human.


I agree that we probably don’t need the conventional features in the future but about completely disappearing I am not sure.

In my mind we’re switching to a workflow where code review at the end will be the most important part.


"Records screen at 1 FPS in 15-second chunks.“

If it’s recording 15 seconds, how often are you doing that? Once every 15m as the analysis interval is 15m?


Looks like it's recording all the time and analyzes 900 screenshots every 15 minutes? And it keeps records for 3 days.

So I'm not sure I buy the lightweight/low-impact claim.


Pricing is really good for this benchmark value. Let’s see how it holds against people testing it.


If this is sonoma-dusk that was on preview on openrouter, it's pretty cool. I've tested it with some code reverse engineering tasks, and it is at or above gpt5-mini level, while being faster. Works well till about 110-130k tokens tasks, then it gets the case of "getthereitis" and finishes the task even if not all constraints are met (i.e. will say I've solved x/400 tests, the rest can be done later)


I can imagine, no model so far could actually use those context sizes…


I was disappointed in its tool calling perf. I didn’t test it extensively though


I have a .co domain and noticed that some people think it’s a typo and adjust it to .com


Not sure if I would follow that point about usability. For me usability means also how usable it is to new people. How usable is the language to a foreign person compared to e.g. Python, Go or even Java - or if you want to mention functional languages like F#?

But besides that I am totally on your side, usability is great.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: