the best would be on device inference only but we need maybe 6 months for a small model to match capabilities yet. I wanted to do it like that but even my pixel 10 suffered.
I live in an earthquake prone area and thought Japan was cutting edge in earthquake protection. Beyond the obvious concern for other human beings, I am interested in why there was so much damage from what I would have thought was still a relatively manageable size earthquake for them. I am here trying to learn a lesson that I would not expect to learn from Venezuelan infrastructure and earthquake response.
It is also the timing of building booms. Problems being exposed have triggered regulations and enforcement in Venezuela but that is relatively recent and much inventory was built decades before.
This is pathologically outside scope. I don't think I have ever seen somebody threaten somebody else on hn before. The 'don't make me do it to you' abuser trope is next level.
I have a problem that it constantly tries to re-encode video that could be played perfectly fine in their player or the mpv shim. I wound up just mounting my remote drives and playing in my local mpv. I don't really use it because of that. Unfortunate because otherwise I love a lot of things about it.
I too have run into this problem on a number of devices. The client's supported codec/media format detection logic appears to be extremely pessimistic. To the point that the mere existence of certain audio track formats and subtitles can trigger transcoding, even when said tracks/subtitles aren't actively used. The same files played via MPV on a file share, i.e. no transcoding possible, play without issue.
I've tried tweaking both the clients and server to be less pessimistic, i.e. see if the active media elements are supported, but even then it really fights it. I think the best approach would be rewrite the clients to adopt a (try || transcode) strategy rather than (guess || transcode), but that looked to be a major piece of work.
You can check why it’s re-encoding, there’s some guides out there. In my case it was the subtitles! Turns out Safari can’t handle all types of subtitles. Might be worth looking into it.
Of course I have been down the rabbit hole. The software is wrong. Give me an option to bypass re-encoding, and instead of failing based on diagnostics like it does, just play the darn file the best you can. I only have so much patience and I prefer living with a samba share to play it in the exact same mpv player without problems rather than fighting software over something that is so simple and fundamental to a video player.
Yeah, I can 100% understand your frustration. It’s also a bit opaque as to why it’s re-encoding.
That said, we are a family so I can’t get everyone else to stream to mpv, so Jellyfin works better for everyone. mpv is also a great piece of software, plays everything!
Actually it does include an important level of review. They say "init a TODO list with a validation step for each item", and then the last several sections of the execution are within the TODO - where it is validating the code.
To me that was the heart of the article and of what they did - create a self-validating todo list that deterministically forces the agents to stay on task, and then trim out just the right extraneous context (the actual planning) without messing with the read-file context which is where they found subagents burning most of their tokens.
Just a few days ago I was speculating about forking context to implement instead of spawning subagents here on hn. This is similar to that just several more steps more sophisticated. You could even fork the trimmed context here for very large tasks.
It wasn’t clear to me (and still isn’t, after slogging through the inhuman article again) that the verification here is done by a separate agent from the implementation. That’s a second trimming step, but in reverse: at that point you want the new code in the context, but not the implementation reasoning.
No idea, but yes it seems like good practice to trim context there as well. A good candidate for v2 if it's not present.
At the same time, even if that is not done, the todo is both specification and tests. If it passes those when it should not, then either you approved something you should not have, or else there should only be smaller improvements to be made. I like the concept enough and I am not very concerned about this, so I will give it a test on a project I have had on backburner for a bit.
I am American who has lived in many countries around the world, and I think this is distinctly wrong and the source of many problems in the US.
It would be more correct to say that the average American values outward displays of nationalism more, and has a more negative perception of those who do not appreciate or want to participate in those displays than people in most other countries. And yes, they conflate this with 'patriotism'. However, this is almost completely performative and lacks real substance, as is proven by the typically far more selfish attitude towards their fellow citizens, and is exemplified by the constant historical failures to provide significant funding for projects designed to help rather than harm others.
Europeans and people from other countries around the world are often fiercely in love with their countries. They just tend not to love the idea of noisily jumping up to gaudily beat their own drum. So yes, the average American thinks they are more nationalistic, when in fact they are just more tribal and crude about their nationalism than what is typically found in other countries around the world. If only our nationalism were taken a bit more seriously than our affiliation with a sports team, which is in theory just for fun and entertainment, that would be an improvement.
I disagree with this, I've noticed that the countries rising to prominence are quite nationalistic and the ones fading into obscurity are very post-national.
> Europeans and people from other countries around the world are often fiercely in love with their countries.
I would also disagree with this, I think it's profoundly uncool to love your country in many parts of Europe—think the UK and especially Germany.
The Europeans that did actually fiercely love their country that I've met were all Poles or Serbs that were gaudily beating their own drum.
What problems do you think arise from nationalism in it's current form in the US?
> I think it's profoundly uncool to love your country in many parts of Europe—think the UK and especially Germany.
I think that's because you're focusing on outward displays in exactly the way GP was talking about. It's profoundly uncool to be a flag-shagger, but Brits do very much love their country deep down, in the ways that really matter.
I don't think they value displaying nationalism more, nationalists tend to be very vocal and visible, it's just that the US is full of nationalists. It really is the biggest issue with the US, and why the orange man is president.
I think you missed my point, which is that in the US, people typically described as nationalists tend to be pseudo-nationalists who value pomp and ceremony, but not substantial concrete actions to better their country or actual real care and love for their fellow countrymen. In terms of percentage of the population who value and love their national identity, we are no different than anywhere else.
Leadership in European countries is so routinely in conflict with their people who understand the inalienable rights of the people so well. I wonder where that comes from.
You're not wrong that the American public is largely out of touch with the fundamentals of a free society.
> Leadership in European countries is so routinely in conflict with their people
> I wonder where that comes from.
> Leadership
Democracy is great but that elected leaders seek reelection at the expense of the common folk isn't something new, those in power will naturally seek more power.
The problem is that Americans look at vulnerable people and billionaires like they individually deserved their fate. The cult of merit.
It seems like there could be a useful strategy of writing a plan with a main agent, and then instead of spawning subagents to implement, fork the main context to write each part. Then use one last fork to verify the work. That way you keep reusing the same context without polluting your main context for when you are ready to continue.
I've started doing this by hand in OpenCode and it works pretty well. But there's no UI support for maintaining a tree of related session forks so there's a little bit of manual fussing involved with session naming to keep organized. I also like to end a session with an "AI-friendly terse but detailed summary" (or some equivalent prompt) that I can then dump out to a Markdown file and then the mainline session can still get info back from the branch session. I don't know how much of this is automatable with OpenCode plugins, or in another hackable harness like Pi.
It seems like they are actually using the subscription providers' respective cli tools and managing context for them. In which case I believe it is not against the ToS any more than invoking codex cli from a custom python script would be? I personally cannot find an openai-hosted clarification, just on hn and x.
reply