HN rank: 1

HN score: 394

comments: 224

original url: https://laurentiugabriel.github.io/blog/articles/how-i-use-llms-to-learn/

评论信号：I thought LLMs were a great tool for learning new topics - perhaps even complex ones. But overtime, I have had several frustrations with this. First, I get exhausted reading LLM prose. I really don't want to read anything generated by something like Opus 5 at this point. Second, as I dive deeper, I need a way to organize the information in a useful way as I begin to branch out in many different directions. I have tried to use the LLM to fix this by having it generate a web page with diagrams and organized information flow. It's an improvement, but I still run into the issues I described in my first pint - LLM prose is annoyingly dense, and the useful information gets lost in a bunch of noise. You can direct it do something like "use plain English and avoid LLM prose - provide only as much information as necessary to demonstrate the point", but it is once again only a marginal improvement.And then I begin to think to myself that I should just read a book on the topic written by a trusted source who put a lot of effort into teaching the topic properly and presenting the information in a thoughtful way.... reply: I have had very similar experience!...

评论信号：> What you get is a beautiful animation that is 100% accurate and free of hallucinations.I'm not sure I follow how this is actually guaranteed? The fact-checking process mentioned just seems to involve asking AI to review its own work. reply: All these LLM-as-review hype pieces don’t acknowledge that it’s turtles all the way down

评论信号：> In plan mode (using CC, or OpenCode) I ask a model to build the foundational knowledge for X topic.Makes sense.> I ask it to review the accuracy of the knowledge base it built in the previous step.Ooookay that sounds good.> I proceed asking it to build a simulation of that topic in a low-poly, Rollercoaster Tycoon-like animation.wat. reply: It's such a surprising and delightful turn, I love it!

HN rank: 2

HN score: 69

comments: 33

original url: https://propelmusic.co.nz/articles/the-sound-went-quiet-nz-music-media

评论信号：There’s a guy in Wellington making a photocopied weekly gig guide which will do more for the local music scene than this attempt at making a profitable social media. I guarantee it.http://www.theimage04.com reply: Its actually a small volunteer crew not one guy, and they are great! We have shared their posts on our socials, they do the guide, a weekly access radio show, free classifieds, all self funded... Which is exactly what Propel exists to support.On the profitable social media bit. I have been a worker in the scene for 8 years, running events, promoting other people, pushing the scene. And i'll keep doing it here because I love it, not because theres money in it.

评论信号：> Live performance revenue reached $329 million, well above pre-Covid levels.Is that inflation-adjusted? And as the article points out, very little of that is local talent, so it's likely some of that's due to the cost of tickets.As someone who lived in NZ (although Wellington) for 10 years until last year, the local music scene was there, but at least in Wellington, the change in the 10 years I was there was considerable: The earthquake in 2016 progressively caused several venues on Cuba Street to close due to building regulations, and Covid was a significant shock as well, with some of the smaller (although most places in Wellington were small!) gig rooms / bars / breweries that would often host bands closing.There was still Valhalla, San Fran, The Rogue & Vagabond and others, but it just didn't feel as much was going on other than for things like Cuba Dupa street festival, etc, or the Jazz weekends that would be held.As the article points out, this is not localised to NZ, it's happening in Australia and the UK as well in terms of venues/pubs closing and live music not being quite the draw it once was because of that. reply: Yep, here in Oz (Victoria) the scene is struggling....

评论信号：I like that this is bringing out all the kiwi accounts. I've never seen so many of us all in one post. Hey guys! I'm a wannabe software engineer who's in Wellington, I had self-taught myself fairly well until LLMs has made me question if I completely wasted my 20s on what could now be a fools dream.Always looking for ways to spread community in our recalcitrant people, I'm not sure this is right direction but it's a goal worth attempting until it works. Well done!

HN rank: 3

HN score: 23

comments: 1

original url: https://publicdomainreview.org/collection/marnameh/

评论信号：> How, one should rightly ask, could a khrafstar like the snake possibly be associated with good fortune?For a while a running joke in Persian Wikipedia community was to call software "bugs", _khrafstar_s.

HN rank: 4

HN score: 554

comments: 250

original url: https://blog.terrygodier.com/2026/08/09/mea-culpa-dark-hours.html

评论信号：On the previous HN posts I got this impression:The developer's astrology app containing tarot reading features was rejected from Apple's App Store that prohibits astrology apps.He then replaced the app's content with a clone of, if not the identical open source astronomy app "Dark Hours", copying even the name. The original is here: https://darkhours.appThe developer was then in contact with John Gruber, who wrote an article claiming Apple's reviewers confuse a nice, scientific astronomy app with astrology. The developer reviewed the article before publication.It then turned out that the developer forgot to mention that originally he did upload an astrology app for review. Gruber felt duped, and noted that it's unclear whether an updated build containing the new astronomy app was ever submitted to Apple for review: https://daringfireball.net/2026/08/retraction_app_store_reje...Now the developer seems to claim that he merely accidentally cloned that open source app when working with Claude.I am not buying it. reply:...

评论信号：Something went seriously wrong there, and I'm not sure it's just Claude copying an existing project bug-for-bug. For more context, see also this post from Gruber at Daring Fireball:https://daringfireball.net/2026/08/retraction_app_store_reje... reply: Yeah... If you even say to Claude I want to make an app like github.com/user/repo it's not gonna just clone it and do some touch ups. Anything can happen of course, but my spidey sense says generally AI won't fork a project unasked (just because of the implied maintenance burden of applying future patches from upstream if nothing else)

评论信号：Yeah, the big bad AI made you plagiarize a whole project down to the name, and lie to everyone about the review process. Not buying any of it. reply: > down to the nameAnd an identical bug, per the Bluesky convo Gruber linked.https://bsky.app/profile/mmmeh.bsky.social/post/3mslc3b3u4c2...

HN rank: 5

HN score: 164

comments: 623

original url: https://news.ycombinator.com/item?id=49233423

评论信号：I got laid off at the end of April and have been building my own personal dream tool since, it's a skeuomorphic carpentry simulator with an agent MCP. You start with real wood specs and a shop full of miter saws, router tables, table saws and the like. Think of it like Sketchup but no extruding rectangles.It's been really fun to build with. Agents can create parametric procedures so e.g. stick framing becomes a simple function call for the next agent, building a flywheel. There is full agent-human parity in every surface, so there is a human UI for the procedures too.Every operation is yaml, so agents pick it up pretty quickly. Agents can also file feature requests when they reach for a tool that doesn't exist. You can export to 3d printing files, video walk-through, step files, get a BOM and a cut plan, view your project in life-size with AR. There is a notion-like interface for authoring build guides... a lot going on. If you're a woodworker/software engineer you might enjoy it.You can add the MCP to your agent of choice, send a picture, description, sketch or whatever; say "build this with Sawdust"https://sawdust.diy reply:...

评论信号：I'm (solo) spinning off the internal agent knowledge and observability layer used at Motion (YC W20, series C, ~40 devs). It was born out of a need to lift all devs using heterogeneous models, harnesses, and prompting styles to a higher level of consistency and quality while surfacing the visibility to see what's working and what's not. The knowledge layer is integrated into the code review layer and all of it tied together with telemetry to the document section level to see how each piece of context is affecting code generation.Open source repo (.NET 10 + C# + Postgres): https://github.com/zeeq-ai/zeeq-appDocs and more info: https://zeeq.ai

评论信号：Launched a suite of media inspection and encoding tools a few months ago, based on FFmpeg. Slowly getting more customers.https://video-commander.comConstantly iterating through refinement and features. It's built on Rust + Tauri with a React frontend, in case anyone is curious.I've created various open-source and commercial tools in the multimedia space over the last 10+ years and wanted to put it all together into something more premium with an IDE-like experience.Most recently I added a /playground area to experiment with the inspection tools via a WASM build, which I thought was a neat way for users to try the app before downloading the full version.Happy to answer any questions!