15:[[38988948,{"by":"qsantos","descendants":202,"id":38988948,"kids":[38989889,38997311,38989717,38994414,38992214,38989730,38998943,38989529,38989734,38997572,38989515,38998705,38995536,38992333,38995740,38996005,38991277,38992423,38992147,39003693,39068979,38991651,38998600,38995491,39003758,39002803,38990067,39000441,38990246,38990044,38996713,38997675,38992217,38995216,38990130,38990692,38992029],"score":468,"time":1705225335,"title":"Dynamic programming is not black magic","type":"story","url":"https://qsantos.fr/2024/01/04/dynamic-programming-is-not-black-magic/"}],[38981529,{"by":"PringleBoy","descendants":1,"id":38981529,"kids":[38988199],"score":1,"text":"This is not a homework problem. What's the best way to approach the following? 0-1 ILP works, but there might be something better:

Imagine you have a checkers board and a bag of black pieces. You want to place the pieces on the chess board so that there are no 4 in a row diagonally, vertically, or horizontally. What is the maximum number of pieces you can put on the board?","time":1705163641,"title":"Combinatorial Problem","type":"story"}],[38968751,{"by":"cstanley","descendants":7,"id":38968751,"kids":[38980261,38977371,38969895,38978661],"score":5,"text":"Big problem, let's break it down...

1. Data issue identification\n2. Solution and implementation

Most issues are discovered in the data warehouse. Entity matching customer data across different systems, some business process results in duplicate, or null data. I know there are existing, non-LLM, products that do this. I'm curious to compare those with new LLM first products.

On solution/implementation. Ideally you're able to fix this in the source system, either in your SaaS tool or in the way you write production data. You can also fix this in the data warehouse, munging/ETL'ing the data. Seems like LLMs could help to 1) identify and recommend a change in an external system, 2) submit a PR to solve this in the data warehouse.

Anyone know anyone working on these problems?","time":1705071495,"title":"Anyone working on LLM tools for enhancing data quality?","type":"story"}],[38974330,{"by":"potta_coffee","descendants":78,"id":38974330,"kids":[38975143,38974810,38974964,38974629,38975243,38975228,38974555,38975240,38974616,38975138,38974973,38975208,38975245,38974989,38975257,38975157,38975275,38975045,38976735,38980138,38975248,38976270,38975186,38975084,38975104,38975251,38974938,38979240,38975178,38976345,38975093,38995601,38975408,38975260,38976724,38974809,38975136,38974861],"score":100,"text":"$16","time":1705094774,"title":"Ask HN: How can I get out of tech?","type":"story"}],[38972032,{"by":"kylebenzle","descendants":39,"id":38972032,"kids":[38973455,38973207,38972364,38978658,38972912,38973423,38987793,38973346,38972762,38975646,38980112],"score":24,"text":"$17","time":1705084681,"title":"Why LLMs are not and probably will not lead to \"AI\" (an opion)","type":"story"}],[38735725,{"by":"pcwelder","descendants":86,"id":38735725,"kids":[38739113,38736642,38736615,38737728,38736995,38736461,38843869,38743066,38741457,38736488,38736566,38741396,38748598,38739570,38741189,38738688,38737799],"score":191,"time":1703262567,"title":"Schrödinger equation emerges mathematically from classical mechanics (2012)","type":"story","url":"https://www.researchgate.net/publication/241778960_A_Pseudo-Quantum_Triad_Schrodinger%27s_Equation_the_Uncertainty_Principle_and_the_Heisenberg_Group"}],[38717114,{"by":"evanhu_","descendants":73,"id":38717114,"kids":[38717371,38717464,38717665,38717967,38717390,38717177,38717755,38719503,38717370,38767324,38718720,38718898,38725518,38717286,38717475,38717454,38719112],"score":194,"text":"Hello HN, Talk2Arxiv is a small open-source RAG application I've been building for a few weeks. To use it just prepend any arxiv.org link with 'talk2' to load the paper into a responsive RAG chat application (e.g. www.arxiv.org/abs/1706.03762 -> www.talk2arxiv.org/abs/1706.03762).

All implementation details are in the GitHub. Currently, because I've opted to extract text from the PDF of the paper rather than reading the LaTeX source code (since I wanted to build a more generic PDF RAG in the process), it struggles with symbolic text / mathematics, and sometimes fails to retrieve the correct context. I appreciate any feedback, and hope people find it useful!

Currently, the backend PDF processing server is only single-threaded so if embedding takes a while please be patient!","time":1703134100,"title":"Show HN: Talk to any ArXiv paper just by changing the URL","type":"story","url":"https://github.com/evanhu1/talk2arxiv"}],[38161538,{"by":"jn31415","descendants":8,"id":38161538,"kids":[38161715,38162457,38169280,38165554,38193255,38181116],"score":7,"text":"For several years now, there have been talks about China catching up or even overtaking Western countries when it comes to innovation. But what concrete signs are there?

I've read multiple times that China is supposedly now a leading publisher of AI research papers. But how come ChatGPT, Stable Diffusion and all these other recent AI innovations didn't come out of China? Even the three giants, Alibaba, Tencent and Baidu seem to be barely able to make a dent in foreign markets (outside of straight acquisitions).

And Temu appears to be burning a lot of cash to do something similar as Wish, which hasn't been doing very well lately.

It would be interesting to hear from people active in all kinds of fields, even outside of software tech.","time":1699272916,"title":"Ask HN: Besides TikTok, what other innovations have come out of China recently?","type":"story"}]]

1.	Method for generating structured images without using diffusion models？ 2 points by hxypqr 2 years ago \| 0 comments
2.	Can LLM be trained like training Go AI? Such as alphago 2 points by hxypqr 2 years ago \| 3 comments

user:	hxypqr
created:	November 8, 2023
karma:	1