TGTGInsighttelegram intelligenceLIVE / telegram public index
Back to channels
DPS Build avatar

TGINSIGHT CHAT

DPS Build

@dps_build

Technologies

AI, coding, data science and startups

Subscribers713Current channel subscribers
Tracked posts603Indexed post count
Recent reach4,305Sum of recent post views
Recent posts

Recent posts

Page 42 of 51 · 603 posts

Posted Mar 27

使用 postgres 的 pgvetor 插件来存储 embedding 数据,作为 LLM 的输入。 https://supabase.com/blog/openai-embeddings-postgres-vector

405 views

Posted Mar 27

一些中外的独立开发者,包括他们的作品和独立开发经历: https://reorx.com/blog/indie-makers-im-following/

385 views

Posted Mar 27

Here we show a proof of concept using OpenAI’s chatgpt-retrieval-plugin with Meta’s LLaMA language model. This is more than just a guide. It is a call-to-action to build an open protocol for foundation model plugins allowing us to share plugins across LLMs, and govern their interactions. https://medium.com/m/global-identity-2?redirectUrl=https%3A%2F%2Fblog.lastmileai.dev%2Fusing-openais-retrieval-plugin-with-llama-d2e0b6732f14

385 views

Posted Mar 27

API 届的 IFTTT https://pipedream.com

367 views

Posted Mar 26

Sparks of Artificial General Intelligence: Early experiments with GPT-4 https://arxiv.org/pdf/2303.12712v1.pdf

347 views

Posted Mar 26

ChatGPT 救了一只狗: In the meantime, it occurred to me that medical diagnostics seemed like the sort of thing GPT4 could potentially be really good at, so I described the situation in great detail. I gave it the actual transcribed blood test results from multiple days, and asked for a diagnosis When we reached the second vet, I asked if it's possible it might be IMHA. The vet agreed that it's a possible diagnosis. They drew blood, where they noticed visible agglutination. After numerous other tests, the diagnosis was confirmed. GPT4 was right. https://twitter.com/peakcooper/status/1639716822680236032

361 views

Posted Mar 26

利用 ChatGPT API 来总结 Sam Altman 的访谈 https://reccap.it/recaps/sam-altman-openai-ceo-on-gpt-4-chatgpt-and-the-future-of-ai-lex-fridman-podcast--38c54630577d44a0b5423d623dccc254

357 views

Posted Mar 26

一个极其详尽的 ML 工程资源 https://madewithml.com/

363 views

Posted Mar 26

Apple 官方的 neural engine 推理加速 SDK — 直接让 PyTorch 的推理速度提速十倍 Use ane_transformers as a reference PyTorch implementation if you are considering deploying your Transformer models on Apple devices with an A14 or newer and M1 or newer chip to achieve up to 10 times…

322 views

Posted Mar 26

微软发布了一整条基于 LLM 的开发链: Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The SK extensible programming model combines natural language semantic functions, traditional code native functions, and embeddings-based memory unlocking new potential and adding value to applications with AI. https://github.com/microsoft/semantic-kernel

333 views

Posted Mar 25

一些朋友们做的技术频道,大家可以按需订阅: https://t.me/sannsaku https://t.me/amneumarkt https://t.me/foreseaz_collection https://t.me/LinghaoCh

334 views

Posted Mar 25

但是对公司而言,让自己跑得更快远比让竞争对手跑得慢一点更重要。所以大部分情况下保密措施应该是以不伤害效率为前提的。对用户数据的保密除外,但是保护用户数据的措施通常不会影响到大部分人的工作效率。 理论上这些都可以被滥用或者误用,但是滥用往往缺乏动机,误用可以从设计上避免。一个大原则是风险可控或可逆的事情默认是没有流程的,只有实际发生了问题,证明必要时才会靠引入流程来解决。有了流程就需要有人审批有人执行,如果它解决的问题不常发生、有其他方案或者产生的危害不如流程带来的成本,那么设立流程就是不理性的。 有的比较卷的团队为了控制代码的复杂度,还把自己 code base 的行数上限放到了测试里。如果有人增加了 10 行代码,就需要重构其他地方的代码来省出 10 行,或者提供一个好的理由来提高上限。 除了日常的 code review 外,每个新员工会需要学习公司的代码规范,并通过工作中会用到的每个语言的可读性 review。方式是准备一个百行以上的 changelist,提交给一个有资格做 readability review 的工程师,通过之后才有权限提交用在生产环境的代码。 所以 Google 把版本管理完全倒了过来,每个项目/组件都只要维护一个最新版,所有的改动最重要的原则是不能破坏任何测试。所以如果有人在一个共享组件里做了向前不兼容的改动,就会需要在同一个 changelist 里把整个代码库里所有调用到这个接口的地方改过来。 GWS 每周会做一次 binary push,也就是二进制文件的发布。流程是每周一早上负责发布的工程师从当前的代码做一个发布分支编译出一个二进制文件,交给 QA 开始测试,发现 bug 就把修复 cherry pick 到发布分支。 https://1byte.io/google-large-scale-dev/

346 views
12•••5•••10•••15•••20•••25•••30•••35•••404142434445•••5051