building https://shellular.dev, an app that let's you use your dev env from anywhere - your agents (Claude Code, Codex. OpenCode, Pi etc.), persistent terminals, local repos and code editor, in-app browser to remotely access localhost:<any-port> and js console for debugging.
I recently swapped to Codex and its pretty great after a day or so of migrating configs and wrangling Codex's bubblewrap and finetuning the auto mode classifier prompt.
Claude is now mostly demoted to Claude Design.
I liked the fact that ChatGPT web chat usage is separate from Codex usage.
The hardest part isn’t payment; the prompt itself may identify you. For truly sensitive topics, I’d abstract the details first, then use a local model—or avoid an LLM entirely.
Right but 2000 to 2010 didn't have similar progress, and especially 2010 to 2020 didn't. Sure, things have gotten better but not as much as the 1990 to 2000 leaps.
And yes, laptop specs haven't changed much and this is partially because the need for spec changes wasn't present, but also during the last 20 years there has been tremendous pressure for efficiency in datacenters.
Despite that, dennard scaling is dead since 20 years. There are physical limits. Already now, the wear effect of electrons jumping is present, and it will only get worse as things scale towards smaller sizes.
There are some benefits to be had, e.g. one can etch models into chips directly so you can pack them more closely, and run more inference on Tensor like chips, but that gives you maybe one order of magnitude improvement in total, at most. Also, of course nobody does that when each 2-6 months a new model comes out.
Yeah, and since it seems there's some competition there, the prices are decent. You can get milled metal, 3D prints, populated PCBs... crazy what you can do now and how quickly it can be turned around, if you are willing to pay.
I wish there were more regional places like PCBWay and JLCPCB in US, EU, etc (with similar pricing) so shipping didn't require circumnavigating the globe.
Regarding 1, I think a) a sizeable fraction of voters are not able to recognize AI-generated text b) many who notice don't care, or are willing to overlook it if the premise is interesting enough. (The latter is true for me, on occasion)
Maybe we need a two-dimensional voting system: good/bad, ai/human. I think the second axis could cut down on meta-discussions over how much of the article was AI-generated.
That will only further increase the stigma surrounding LLMs. On Lobsters it actually got to the point where I no longer felt welcome on the site, even though I don't use LLMs to generate articles. The constant "this is AI slop" commentary is noisy and tiresome as well.
But maybe you should checkout the tools it’s based on, sem - https://github.com/Ataraxy-Labs/sem and ultimately treesitter. They at least give a more structured approach to dealing with code than simple text.
Dutch people went all in on the dot com bubble. After that debacle Dutch citizens swore off the stock market for an entire generation despite economists literally begging folks to put their money back in (the Netherlands has a rather obscene amount of money tucked away in savings accounts).
Comments moved to https://news.ycombinator.com/item?id=48834309, which was posted first. (Sorry! I still want to implement karma sharing so we can split credit between multiple submitters.)
As far as I understand, "flagging" is intended for things that break the guidelines. AI-generated content is explicitly banned, but only in comments, not submissions.
I think it would be great if AI-generated submissions were outright banned as they fundamentally break the balance of effort that HN was built upon, but as was already stated by another user, YC is heavily invested in AI so there's a conflict of interest there.
I don't think software companies ship UI churn because they're running out of things to do with their development resources. They're just bad at rewarding bug fixing and bad at saying no to user-visible changes that aren't meaningful improvements big enough to overcome the pain of making users re-learn a changed UI. Microsoft doesn't need to scale down their Windows development resources, they just need to make them do the less-fun parts of their jobs instead of shipping new intern project rewrites of Notepad.
Setting aside that this is subjective, I think it’s safe to say that from the POV of most of this site’s target audiences, that “start” happened a long time ago. PG’s essay on submarine articles didn’t come out of nowhere, and he hasn’t been active here in…a decade? Ish?
I released 3 games my friend designed, and built a game framework in WebAssembly for building them. Some 9 or 10 months ago I asked my friend (legendary game designer Mike Elliott) if he wanted to work through his backlog of designs he has that he'd love to see brought to life. I'm very protective of my family life and dedicate a lot of my time to it, and have a normal full time job, and so LLM-agents really enabled being able to make stuff like this happen in a reasonable timeframe just working on and off in my free time.
I started them with ebitengine (Golang) but got somewhat frustrated with its web builds, and so built my own thing for small games that I want to work great on mobile or native PC, but also on web. I call it NanoGame, the host is written in Rust and the games are AssemblyScript. I've ported a number of other small games I had written to it as well, but haven't released any.
Two of the games I released a couple days ago were actually the ebitengine versions, but have partial ports to my framework, and the third I released the version using my stuff.
https://scramblequest.app - ebitengine, word search game where you slay monsters with the words, has a long campaign as well as a daily challenge and unlimited play
https://wordpeek.app - ebitengine, another word search game, this one reveals pieces of a picture and your goal is to guess the picture
https://playsilhouette.app - my own framework, this is a simple matching/hidden object(ish) game, more for kids
the worlds GDP is like $120,000,000,000,000. Her work is worthless in comparison. the only possible benefit of concentrated wealth is taking concentrated bets on a new research or technology or social organization. But to give to generic charities is a waste of time and reveals a profound lack of creativity on her part.
The recent rule addition to the Guidelines says this: "Don't post generated text or AI-edited text. HN is for conversation between humans." And I think that covers comments, but I'd be happy to see it also cover articles that are blatantly and primarily if not exclusively AI-generated. But how much AI is permitted? For instance: I'm writing a blog post now. It's all mine. If I include an AI-generated cartoon at the end, just to illustrate something, but not to be the whole or primary point of the article, is that AI-generated? Would the rule be conservative in nature to the extent that mostly human but clearly also AI-enhanced might get flagged but it's in the discretion of the moderators? How would you propose enforcing as to articles (versus comments which are usually quite obvious and thankfully have pretty much stopped being AI-generated since the rule was implemented, for the most part)?
I've been working with coding agents for a few years and became increasingly frustrated by the way it pushes you towards a solution. So I built rubberduck (https://userubberduck.com/) - a way to control exactly what solution the agent ends up creating by mimicking a design conversation with a competent colleague where the agent explores the solution space together and forces you to make decisions. The final output is a consolidated design document of all the decisions you made. At least that was how it began. I've since built an implementation plan step where it figures out how to translate the design to code and execution where it actually builds it. All of this happens in a properly isolated environment (using gVisor under the hood). There are more features I want to build so on it goes I suppose.
I was not in any way intending to imply I thought that, I was using the language above about economic value. I've edited my post to avoid the misunderstanding, I think you and I are aligned.
Somehow millions of people have learned physics in a "straight-line" at university. Most physics majors have a logical progression from the simplest to most complex ideas.
Ai will fall apart as an industry but it's likely that models on par with e.g. opus 4.8 will be runnable on a home server within the next year and a half and that model hosts will still exist. I figure these tools aren't likely to go away.
100% remote unless absolutely required. Professions like doctors, cooks, massage therapists. This will clear 95% of traffic. Start with mandatory remote for all software jobs.
