yang

Long in self-evolving systems. Do a little bit about technology work

[停雲 @tingyun97]

互联网牛马的那些术语，这图表达很到位。

[yang @hibaiyang]

good stuff. ai should be engaged in more advanced intellectual work. instead of low leveled junior labor which brings about large shitty workout or e junk

[Andrej Karpathy @karpathy]

Transforming human knowledge, sensors and actuators from human-first and human-legible to LLM-first and LLM-legible is a beautiful space with so much potential and so much can be done...

One example I'm obsessed with recently - for every textbook pdf/epub, there is a perfect "LLMification" of it intended not for human but for an LLM (though it is a non-trivial transformation that would need human in the loop involvement).

- All of the exposition is extracted into a markdown document, including all latex, styling (bold/italic), tables, lists, etc. All of the figures are extracted as images.
- All worked problems get extracted into SFT examples. Any referenced made to previous figures/tables/etc. are parsed and included.
- All practice problems are extracted into environment examples for RL. The correct answers are located in the answer key and attached. Any additional information is added as "answer key" for a potential LLM judge.
- Synthetic data expansion. For every specific problem, you can create an infinite problem generator, which emits problems of that type. For example, if a problem is "What is the angle between the hour and minute hands at 9am?" , you can imagine generalizing that to any arbitrary time and calculating answers using Python code, and possibly generating synthetic variations of the prompt text.
- All of the data above could be nicely indexed and embedded into a RAG database for later reference, or maybe MCP servers that make it available.

Then just as a (human) student could take a high school physics course, an LLM could take it in the exact same way. This would be a significantly richer source of legible, workable information for an LLM than just something like pdf-to-text (current prevailing practice), which simply asks the LLM to predict the textbook content top to bottom token by token (umm - lame).

As just a quick and crappy example of synthetic variations of the above example, GPT-5 gave me this problem generator (see image), which can now generalize that problem template to many variations:

- When the time is 11:07 a.m., what is the degree measure of the angle between the hands? (Answer: 68)
- Determine the angle in degrees between the clock’s hands at 4:14 a.m.. (Answer: 43)
- What angle do the clock hands form when the time reads 11:47 a.m.? (Answer: 71)
- At 7:02 a.m., what angle separates the hour hand and the minute hand? (Answer: 161)
- At 4:14 a.m., calculate the angle made between the two hands. (Answer: 43)
- What angle is formed by the hands of a clock at 4:45 p.m.? (Answer: 127)
- What is the angle between the hour and minute hands at 8:37 p.m.? (Answer: 36)
(infinite practice problems can be created...)

[yang @hibaiyang]

logo free

[Fei-Fei Li @drfeifei]

Check out our newly released WorldScore, by our @StanfordSVL team on benchmarking world models!!❤️‍🔥🌎🏆

[Jo Kristian Bergum @jobergum]

Everyone slap "AI" on whatever they're selling—from laundry machines to data warehouses.

If you're buying a laundry machine, you look for reliability, capacity, and cost.

You care that it works, lasts, and doesn't break.

Nobody buys a laundry machine because it has "AI".

[yang @hibaiyang]

of course. generosity is the enemy of availability. especially when performance is not stable which adds up to unuseful

[yang @hibaiyang]

missed the part

[Tansu Yegen @TansuYegen]

The motorcyclist got stuck in the barrier while trying to catch up before it closed. He then thought he found a solutio...

[yang @hibaiyang]

winner

[yang @hibaiyang]

specifically some health care service needs ai productivity

[yang @hibaiyang]

CICD很重要

[yang @hibaiyang]

@JeffDean cool

[yang @hibaiyang]

in general modern nn method serves as way of stacking computation layer and gives a way to combine different branch like algebra, calculus, geometry, stochastic of “math” in a word

[yang @hibaiyang]

@tunguz we only need xgboost

[yang @hibaiyang]

should we assemble anti-AGI army to defend us from silicon creature. it's horrible when think deeply😱

[yang @hibaiyang]

distillation of llama 6B let me remember of compressing large scale discrete logistic regression into single decision tree model in bank marketing scene about 9 years ago. both are using one model prediction to teach another

[yang @hibaiyang]

@ZeweiChu 拜读，手哥🙏

[PupScanLA @PupscanLA]

Craziest Parts of The Police #Pursuit

[yang @hibaiyang]

@DataChaz excellent in chinese

[yang @hibaiyang]

@tunguz git pull tomorrow