Shann0nC

[Shann0nC @soo_loo8210]

水印已经慢慢形成了

[Hacker News @hackernews]

Many of us are now using coding agents everyday and, it would seem, GitHub pull requests are developing a bit of an accent as a result.

An analysis of 47,000 PRs found a distinct vocabulary cluster dominated by words like “load-bearing,” “quietly,” “latent,” and “genuine" that grew from 1% of the corpus in January to 45% today.

The project samples 100 PRs a day, filters out bot and agent accounts, and groups descriptions into eight different writing styles based on word choice. For those of us familiar with their work, this cluster certainly sounds like the "load-bearing" vocab of LLMs.

https://t.co/4PeC2mPZ23

[Shann0nC @soo_loo8210]

@chenchengpro 您好呀，想请问一下，那在这种时代背景下，cs学习路径会变化成什么样呢？或者说如果想在这个时代下更好的完成人类的角色应该怎么学呢？

[Shann0nC @soo_loo8210]

@phodal 猛烈投递了😄

[Shann0nC @soo_loo8210]

@gamesonrblx yeah！

[Shann0nC @soo_loo8210]

@wong2__ 时间有点太小了，或者可以做一个reset倒计时？

[Shann0nC @soo_loo8210]

@mask8789 @GKev1n 自然周重置吗？

[Shann0nC @soo_loo8210]

@vikingmute 很难相信他，我已经周重置了，说实话最佳策略是自然周重置之后赶紧用，等他送reset，但是我不敢相信他会不会送，所以没有fast

[Shann0nC @soo_loo8210]

@IndieDevHailey 原帖说法核查结果Wi‑Fi 信号可以感知人体真的。CSI 确实能在受控环境中检测存在、移动，甚至研究人体姿态视频展示了真实穿墙识别假的。

[Shann0nC @soo_loo8210]

@IndieDevHailey 5.6SOL 结论：这条帖子的核心叙述不是真的，属于“真实技术原理 + 模拟演示 + 严重夸大成品能力”。
RuView 不是完全空壳，但它远没有达到“靠家里普通路由器看清隔壁人在走路还是躺着”的程度。

[Shann0nC @soo_loo8210]

https://t.co/lopKRhVv7N

[Shann0nC @soo_loo8210]

@techeconomyana typeless需要按键开始说话有点不typeless，希望未来更加typeless

[Shann0nC @soo_loo8210]

@canghe https://t.co/rHTA7OjqJC 做了个把token消耗量转化成qq等级的小产品，大家可以玩玩看哈哈

[Shann0nC @soo_loo8210]

@Lonely__MH nice我收到啦

[Shann0nC @soo_loo8210]

一代人有一代人的鸡蛋要领

[Shann0nC @soo_loo8210]

@chunxiangai 感觉这个PM的ego太大了，在自己的幻想中完成了产品设计

[Andrej Karpathy @karpathy]

One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.

[Shann0nC @soo_loo8210]

@thsottiaux https://t.co/KiRwGsAeYJ