三度佳饮

[三度佳饮 @3DegCelsius]

@Formulasearch 纯民科

[jessald @jessald]

Experimenting with graph layouts.
https://t.co/c8QnkD5fGJ

[Aaronia AG @Aaronia_AG]

PCB Magic, that's all 😍
#aaronia #rf #tech #sigint #PCB #IMS2026 #AMD #Intel #ADI

[三度佳饮 @3DegCelsius]

@MimeOsen 你用什么相机？

[Sakana AI @SakanaAILabs]

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

https://t.co/c9AvsRKybj

What if we didn’t have to hold an entire neural network in memory to train it?

Standard neural net training optimizes all parameters jointly. As a result, the memory required during training grows linearly with the depth of the network.

In our #ICLR2026 paper, we propose DiffusionBlocks, a principled framework to train networks one block at a time, drastically reducing memory requirements while matching end-to-end performance.

With DiffusionBlocks, we split the network into blocks and train them one at a time, so you only need memory for a single block.

How? We explicitly assign each block a role: to move the representation a little closer to the target than the block before it did. That role turns out to be precisely what a diffusion model does, step by step. Each block only needs to optimize its own objective and can be trained independently.

We validated this across five different architectures:

• ViT
• DiT
• Masked diffusion
• Autoregressive transformers
• Recurrent-depth transformers

In each case, performance is competitive with end-to-end training while using a fraction of the memory.

This perspective also extends naturally to recurrent-depth (Looped) transformers, which apply the same network iteratively and normally require expensive backpropagation through time (BPTT). Viewed through DiffusionBlocks, we can replace those multiple iterations with a single forward pass during training.

Read our paper and code, to learn more.

Paper: https://t.co/CRj96VGYQn
GitHub: https://t.co/eNW0K9Xh8E
🐟

[Chang Wei 昌维 @changwei1006]

你知道这段乱码是什么吗？
他是用于验证Email地址是否合法（符合RFC 822标准）的正则表达式
https://t.co/lxQNoAdmyD

[Tom Dörr @tom_doerr]

Covers full academic research pipeline for Claude Code

https://t.co/4Mk2QHXMFg

[How To Prompt @HowToPrompt__]

someone open-source a 1.7b parameter model that parses literally anything.

text, tables, formulas, images, and pdfs in `100+ languages.

100% open-source.

[三度佳饮 @3DegCelsius]

@Kellyv_ai 不知道在忙些什么。

[左子祯 @zuozizhen]

这个号称完美主义者的 UI 框架细节确实到位，包括这种带 Icon 的按钮左右间距看起来视觉不平衡的细节都考虑到了，AI 是真的做不到这个程度啊

https://t.co/FqWTlmSn6P

[陈成 @chenchengpro]

Mozilla 的 Readability 已经名存实亡。

Obsidian 创始人 kepano 写了个替代品：Defuddle——从任意网页提取干净 Markdown 的开源库。

刚更新的最新版加了一个我觉得很实用的功能：直接解析 YouTube 链接，返回带时间戳、章节、说话人识别的 Markdown 字幕，不需要任何 API，��是直接从 YouTube 拿字幕然后整理干净。

对比 Readability，Defuddle 的优势：

• 输出结构化 frontmatter（作者、发布日期等）
• 支持脚注、LaTeX、Callout 块
• 利用网站移动端样式来识别噪音元素
• 可以跑在任何地方：curl、CLI、Node、浏览器、自托管

用法很简单，一行命令就能跑：
npx defuddle parse <任意 URL>

也已经集成进 Obsidian Web Clipper 1.1.0，新增了 Reader 模式和 {{transcript}} 变量，可以直接在笔记模板里用 YouTube 字幕。

MIT 协议，3.3k stars，还在活跃开发：
https://t.co/W1uNHYWVER

[Andrej Karpathy @karpathy]

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, today I measured that the leaderboard's "Time to GPT-2" drops from 2.02 hours to 1.80 hours (~11% improvement), this will be the new leaderboard entry. So yes, these are real improvements and they make an actual difference. I am mildly surprised that my very first naive attempt already worked this well on top of what I thought was already a fairly manually well-tuned project.

This is a first for me because I am very used to doing the iterative optimization of neural network training manually. You come up with ideas, you implement them, you check if they work (better validation loss), you come up with new ideas based on that, you read some papers for inspiration, etc etc. This is the bread and butter of what I do daily for 2 decades. Seeing the agent do this entire workflow end-to-end and all by itself as it worked through approx. 700 changes autonomously is wild. It really looked at the sequence of results of experiments and used that to plan the next ones. It's not novel, ground-breaking "research" (yet), but all the adjustments are "real", I didn't find them manually previously, and they stack up and actually improved nanochat. Among the bigger things e.g.:

- It noticed an oversight that my parameterless QKnorm didn't have a scaler multiplier attached, so my attention was too diffuse. The agent found multipliers to sharpen it, pointing to future work.
- It found that the Value Embeddings really like regularization and I wasn't applying any (oops).
- It found that my banded attention was too conservative (i forgot to tune it).
- It found that AdamW betas were all messed up.
- It tuned the weight decay schedule.
- It tuned the network initialization.

This is on top of all the tuning I've already done over a good amount of time. The exact commit is here, from this "round 1" of autoresearch. I am going to kick off "round 2", and in parallel I am looking at how multiple agents can collaborate to unlock parallelism.
https://t.co/WAz8aIztKT

All LLM frontier labs will do this. It's the final boss battle. It's a lot more complex at scale of course - you don't just have a single train. py file to tune. But doing it is "just engineering" and it's going to work. You spin up a swarm of agents, you have them collaborate to tune smaller models, you promote the most promising ideas to increasingly larger scales, and humans (optionally) contribute on the edges.

And more generally, *any* metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.

[Wey Gu 古思为 @wey_gu]

google cloud 也给了一个 memory agent 的开源实现

https://t.co/CRZyXTIScA

[Andrej Karpathy @karpathy]

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:

- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)

The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.

https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)

[三度佳饮 @3DegCelsius]

@jerryjliu0 Just use MinerU
https://t.co/BuTiX2QYFe

stop building new bs wheels

[Steven Tey @steventey]

This 2D → 3D map animation on @vercel's new CDN dashboard is absolutely magical ✨🤤

[三度佳饮 @3DegCelsius]

@izodic @CuiMao @grok 推荐用海外版 qwen chat，不要用千问 app

[Tom Dörr @tom_doerr]

Converts PDFs to Markdown at 100 pages per second on CPUs

https://t.co/2XTXTXaHrO

[0x鸣人 @LuBtc888]

查理·芒格把家族的钱交给了谁打理？不是巴菲特，而是一个叫李录的华人。

这个在过去几十年里封神的顶级投资家，低调到全网几乎找不到他哪怕一分钟的公开录像。

直到这段被封存了近20年的“禁片级”哥大内部授课流出。

整整一个半时，没有教你怎么看K线，没有教你怎么追热点。

只用框架与判断力讲透两个字：估值。

真正的大师课，值得反���学习。

芒格的个人的外部家族资产，并没有交给巴菲特去设立基金运作，而是唯独看中了李录。

芒格一生中个人的钱只投了三个地方：伯克希尔(他自己的公司)、好市多(Costco)，以及李录的基金。

他还曾在公开场合称呼李录为“中国的巴菲特”。