ᕼᑎ #1wallhop.io145 pts65 commentsProgrammingworth reading

WallHop – 12ft.io is gone, so I built a replacement

echo@mulan ~/hn/story-1

HN 热门故事「WallHop – 12ft.io is gone, so I built a replacement」进入今日前列,值得先打开原文和讨论串判断它真正有价值的部分。

模型分析没有产出可用结构化结果;页面保留了 HN 热度、原文入口和讨论信号,避免用空泛总结替代一手材料。

它在 HN 上获得约 145 分和 65 条评论,说明这个话题至少触发了社区讨论;真正的判断仍要回到原文证据和评论区的分歧点。

这是一条降级分析:它不冒充完整解读,只把可验证的元数据、原始链接和 HN 讨论保留下来,方便稍后重新生成或人工阅读。

评论区已经提供了一些读者反应,但这里还没有形成完整综合。

  • 评论信号:It is not working onhttps://www.thehindu.com/news/national/tamil-nadu/two-seats-...

  • 评论信号:Why not open source? You modified GPL-3 ladder; I don’t know whether it’s legally required, but I feel it’s morally expected and important in practice (since yours may get taken down). reply: https://github.com/wasi-master/13ft is already open sourced

  • 评论信号:12ft? Does anyone use that? Not around here, archive.today standard.It's fast, nice. But trustworthy? There's so little indication that the content hasn't been tampered with or even when it was scraped.

它进入 HN 前列本身就是一个社区信号,但这还不是结论;更可靠的判断来自原文细节和评论区反例。

这条记录目前缺少模型生成的深层解读。更好的阅读方式是先问:它的热度来自真正的新信息、可迁移的方法,还是只来自标题与时机。

可以先读原文第一屏和 HN 最高赞评论,再决定是否值得重新生成完整分析。

ᕼᑎ #2nishtahir.com159 pts31 commentsProgrammingworth reading

Build your own decision model

echo@mulan ~/hn/story-2

HN 热门故事「Build your own decision model」进入今日前列,值得先打开原文和讨论串判断它真正有价值的部分。

模型分析没有产出可用结构化结果;页面保留了 HN 热度、原文入口和讨论信号,避免用空泛总结替代一手材料。

它在 HN 上获得约 159 分和 31 条评论,说明这个话题至少触发了社区讨论;真正的判断仍要回到原文证据和评论区的分歧点。

这是一条降级分析:它不冒充完整解读,只把可验证的元数据、原始链接和 HN 讨论保留下来,方便稍后重新生成或人工阅读。

评论区已经提供了一些读者反应,但这里还没有形成完整综合。

  • 评论信号:I saw Jev and without understanding it said to myself, “I can build that!” And brainstormed some weird Alex trebek jeopardy generator I called trebek, a bun ran typescript app that you give it an input, it decides if it’s a category, question or answer then generates what’s missing. Trained a SQLite-vec database on the English language for a few days with a small qwen embedding model to add vec embeds to the db then ripped the cord on the embeddings before I started feeding my llm the proper specs for Jev and now i have a cool jeopardy generator that now doubles as a Jev clone classifier with a custom v1 endpoint for system 0 or whatever it is. Level understanding here, fun experiment though ^>^ and produces useful outputs

  • 评论信号:This is very cool. If you are looking for something similar but more lightweight, that you can run (and train) on CPU, try out Jeffy: https://jeffyclassify.com/On GitHub: https://github.com/nicobrenner/jeffy reply: Cool project too. If you are looking for a 500MB instead of gigabytes, with evals on Jevbench that you can run fast on CPU check out gutsy.https://github.com/kouhxp/gutsy

  • 评论信号:These are neat - and the source of the many Jev clones we've seen. I think their recent funding round is in part because of their algorithms/data. It remains to be seen if that's a big enough edge to be worth 1 billion+ dollars

它进入 HN 前列本身就是一个社区信号,但这还不是结论;更可靠的判断来自原文细节和评论区反例。

这条记录目前缺少模型生成的深层解读。更好的阅读方式是先问:它的热度来自真正的新信息、可迁移的方法,还是只来自标题与时机。

可以先读原文第一屏和 HN 最高赞评论,再决定是否值得重新生成完整分析。

ᕼᑎ #3momo5502.com49 pts30 commentsAIworth reading

500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter

echo@mulan ~/hn/story-3

HN 热门故事「500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter」进入今日前列,值得先打开原文和讨论串判断它真正有价值的部分。

模型分析没有产出可用结构化结果;页面保留了 HN 热度、原文入口和讨论信号,避免用空泛总结替代一手材料。

它在 HN 上获得约 49 分和 30 条评论,说明这个话题至少触发了社区讨论;真正的判断仍要回到原文证据和评论区的分歧点。

这是一条降级分析:它不冒充完整解读,只把可验证的元数据、原始链接和 HN 讨论保留下来,方便稍后重新生成或人工阅读。

评论区已经提供了一些读者反应,但这里还没有形成完整综合。

  • 评论信号:Unless you explicitly need byte-matching decompilation, there are significantly faster ways to produce a decompilation/C which is functionally equivalent. I need to post about this. What's been working for me is that for every function, Agent A is tasked with writing some code which is semantically equivalent to the original assembly, but not necessarily exactly the same. Agent A also writes tests. Agent A submits the implementation of the function and tests to the harness for it to judge. The harness runs both the original function and the submitted function in a virtual machine/simulator/emulator (the tests define function inputs and starting state). The harness will only accept the implementation if 1) the read/write sequence to RAM is identical to the original function's, and 2) there must be complete line and branch coverage of the original function being decompiled.I've found this to be robust for decompiling games, while giving the agents enough freedom to write code that is readable and not waste a ton of time making sure e.g. instruction ordering, register assignments, etc. are all exactly the same.... reply:...

  • 评论信号:The reason this cost so much is because the AI has the ridiculous goal of getting identical assembly output.The agents would have had to mess around with compiler versions, optimisation options, and the phase of the moon as well.If you just went for functional equivalence, it would probably cost 10x or 100x less tokens.Another false economy was using Sonnet instead of a more intelligent model like Sol 6.1 (1), which would have cost more per token, but is 100x or so better at reverse engineering and coding and therefore can chew through the source code much quicker and make fewer mistakes, meaning less work needing to be scrapped.In my testing doing a similar task, I ran multiple sonnet for weeks and burnt through ~$1000 in tokens to get 20% completion and output that was pretty bad. After switching to Sol 6.1, it finished the whole task in around 2 days, cost around $50, and it did it with zero supervision and a single /goal.(1): struggle to use Opus for reverse engineering, too many safeguards. OAI has virtually none, and uses way less tokens so is more economical. reply: Identical output isn’t ridiculous....

  • 评论信号:I struggle to understand what legal leverage they used to threaten him to remove every detail about the game. Can someone post the game name and company name?So, if you reverse-engineer game X and post reverse-engineered code, what exactly do you infringe, how and in which jurisdiction? What changes if it is done via LLM?(I understand that LLM decompilation is absolutely out of hand right now and something surely will come to trample the fun. But what and when? I suppose american LLMs will have their system prompt updated to forbid any reversing help and report suspicious activity straight to legal hotline) reply: Call of Duty: Modern Warfare 2 (2009) (from a previous version of the page)

它进入 HN 前列本身就是一个社区信号,但这还不是结论;更可靠的判断来自原文细节和评论区反例。

这条记录目前缺少模型生成的深层解读。更好的阅读方式是先问:它的热度来自真正的新信息、可迁移的方法,还是只来自标题与时机。

可以先读原文第一屏和 HN 最高赞评论,再决定是否值得重新生成完整分析。

ᕼᑎ #4patkerr.co.uk382 pts85 commentsProgrammingworth reading

2D Vehicles

echo@mulan ~/hn/story-4

HN 热门故事「2D Vehicles」进入今日前列,值得先打开原文和讨论串判断它真正有价值的部分。

模型分析没有产出可用结构化结果;页面保留了 HN 热度、原文入口和讨论信号,避免用空泛总结替代一手材料。

它在 HN 上获得约 382 分和 85 条评论,说明这个话题至少触发了社区讨论;真正的判断仍要回到原文证据和评论区的分歧点。

这是一条降级分析:它不冒充完整解读,只把可验证的元数据、原始链接和 HN 讨论保留下来,方便稍后重新生成或人工阅读。

评论区已经提供了一些读者反应,但这里还没有形成完整综合。

  • 评论信号:When mentioning foundational 2d driving models one simply can't omit Marco Monster (2003) [1].Also Physics for Game Developers (2001) had a hilarious chapter dedicated to car racing simulation. Most of the chapter is dedicated building the scene in a minute detail - for instance pointing out that the center of gravity of the car will change during the course due to fuel consumption - only to simplify and cancel out most things at the end to leave the reader with just a handful of variables.[1] https://www.asawicki.info/Mirror/Car%20Physics%20for%20Games... reply: Let's not forget Dr. Brian Beckman's The Physics of Racing Series, at the time he was a researcher working at Microsoft on the Forza video game series.https://www.youtube.com/watch?v=I8GQCZgCNw8I built an OpenGL car physics simulation as an undergrad as a project (pre-Claude). It was very fun.

  • 评论信号:I'm sorry, I really want to like and understand this, but the diagrams are worthless and mostly incomprehensible.I would've liked to understand more about why it works the way it does, how it achieved the correct feel etc, not just regurgitate whatever the code does.I would've liked to know more about how the author achieved what they did, not a blog post anyone with an llm could've written. reply: The diagrams seem to have been written (or generated[1]) while looking at the project source code, and use the sort of bass-ackwards approach to code documentation of giving a “post-hoc summation” that only makes sense when you’ve already read the code, rather than serving as an introduction to the code for someone who hasn’t read it yet.That being said, AFAICT, the diagrams are also basically irrelevant to the article in its capacity as a high-level overview of the project. You can just ignore them for the purpose of reading the article.It’s when digging into the project source code that you should look at those diagrams, and then feel frustrated by how much they suck....

  • 评论信号:GTA I and II had really fun car physics. Just driving around and evading police was fun, in a way the later 3d games in the series didn't quite capture for me reply: I still remember GTA 2 had the best radioLaughing vampires dance!

它进入 HN 前列本身就是一个社区信号,但这还不是结论;更可靠的判断来自原文细节和评论区反例。

这条记录目前缺少模型生成的深层解读。更好的阅读方式是先问:它的热度来自真正的新信息、可迁移的方法,还是只来自标题与时机。

可以先读原文第一屏和 HN 最高赞评论,再决定是否值得重新生成完整分析。

ᕼᑎ #5housing.over.pizza221 pts81 commentsProgrammingworth reading

A city-building game in which the city would prefer you didn't

echo@mulan ~/hn/story-5

HN 热门故事「A city-building game in which the city would prefer you didn't」进入今日前列,值得先打开原文和讨论串判断它真正有价值的部分。

模型分析没有产出可用结构化结果;页面保留了 HN 热度、原文入口和讨论信号,避免用空泛总结替代一手材料。

它在 HN 上获得约 221 分和 81 条评论,说明这个话题至少触发了社区讨论;真正的判断仍要回到原文证据和评论区的分歧点。

这是一条降级分析:它不冒充完整解读,只把可验证的元数据、原始链接和 HN 讨论保留下来,方便稍后重新生成或人工阅读。

评论区已经提供了一些读者反应,但这里还没有形成完整综合。

  • 评论信号:Reminds me of that Factorio joke mod which adds bureaucracy-processing as a recipe tree. Assemblers start to shut down if you don't process paperwork fast enough. IIRC, it had biters following the player around in queues to give them complaint forms.

  • 评论信号:The best I got:Discretionary Review (Developer): I built 4,147 homes in San Francisco, 2015 to 2031. Grade A, "Builder of Some Things". Survived all eight investor reviews. 16 hearings, 3 appeals, 4 lawsuits. The city needed 82,069. reply: What's your "build order"? I can usually get permits for something, but struggle getting the 40 units started by the second one (if I do get permits, it doesn't pencil).

  • 评论信号:Whoever made this, I love you and we should be friends.

它进入 HN 前列本身就是一个社区信号,但这还不是结论;更可靠的判断来自原文细节和评论区反例。

这条记录目前缺少模型生成的深层解读。更好的阅读方式是先问:它的热度来自真正的新信息、可迁移的方法,还是只来自标题与时机。

可以先读原文第一屏和 HN 最高赞评论,再决定是否值得重新生成完整分析。