Explorer

i was going to do a video but got lazy

VC by day @untappedvc, builder by night: @babyagi_, @pippinlovesyou @pixelbeastsnft. Build-in-public log: https://t.co/UdHHGbZba5

Yohei

Fri Oct 31 23:36:13

frankly it’s a bit surreal to be in a domain that suddenly attract well-known youtubers and rap singers and yet you’re painfully aware it’s all holding up with duct tapes and strings

there isn’t any good data for training, don’t trust evals, please write a manual patch to [major library], ah and we just learnt the data types are all wrong.

Alexander Doria

Fri Oct 31 23:33:52

solution: it’s six times over ten sentences

Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.

Omar Khattab

Fri Oct 31 23:32:47

Ok, first time using Coolify. Quite a learning curve lol. Like it so far though

Building aismarty, Ai agents and LLM Sauce. Unix Nerd + dev 30yr .Now C++, PHP, React, JS, Python, Typescript++ SAAS fanatic .Fun=PPL Pilot NR IR(R)

Andrew C

Fri Oct 31 23:32:43

RT @MaximeRivest: dspy in R almost summoned itself last night. its only a matter of time.

Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.

Omar Khattab

Fri Oct 31 23:31:52

腾讯刚发布了歌曲生成模型 SongBloom-2B 的改进版本 songbloom_full_240s ! 最大支持4分钟音乐生成。同时还发更新了生成框架，也叫SongBloom，从介绍看是一个自回归扩散模型，官方说既有 diffusion 模型的精度又有语言模型的扩展性，内部生成会从乐曲短片段逐步扩展为完整乐曲。这个模型需要按照格式输入歌词和参考音频，就能克隆歌曲风格。另外模型也发布到了 huggingface 上的个人空间中。也没demo space，所以我也没有特别方便的方式给大家录demo了。感兴趣的同学可以把模型下载下来自己运行试试，毕竟2B大小，CPU就能跑。地址：

A coder, road bike rider, server fortune teller, electronic waste collector, co-founder of KCORES, ex-director at IllaSoft, KingsoftOffice, Juejin.

karminski-牙医

Fri Oct 31 23:31:13

Newest first — browse tweet threads