Jia-Ying Lin

Doing enterprise software.

[ImsUgreeTW @ConradYu5]

10年前，是誰在護航頂新廢油？ 是誰在專案報告時突然就宣布散會？ 就是國民黨立委王育敏，是當大家都失憶嗎

完整質詢：
https://t.co/qXBhC3IU5L

[célina @hanouticelina]

If you like Claude Code or Codex, you should seriously consider running Agents locally as well! The latest small models (like Qwen 3.5) made this a real before/after moment - and the gap keeps closing. Local coding agents are faster, with more reliable tool calling capabilities, still private, and cost $0 in API bills.

We made it super easy for you to run a local agent with the 𝚊𝚐𝚎𝚗𝚝𝚜 Hugging Face CLI extension - a one-liner that uses 𝚕𝚕𝚖𝚏𝚒𝚝 to detect your hardware and pick the best model and quant, spins up a 𝚕𝚕𝚊𝚖𝚊.𝚌𝚙𝚙 server, and launches Pi (the agent behind OpenClaw 🦞).
One command to find what runs on your hardware and go straight to a working local coding agent!

You should give it a try! 👇

[Thariq @trq212]

We've added a new command to Claude Code called /insights

When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.

[Jia-Ying Lin @linekin]

Gemini Pro 4個月免費試用

[N. Taylor Mullen @ntaylormullen]

Gemini CLI + Google AI Pro == significantly higher quotas now

Worked with the team to get some freebies. Here’s a 4-month free trial. Enjoy

https://t.co/XvwtyyaLSk

Thanks to @vickykansal for helping get this done!

[Akari Asai @AkariAsai]

1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 @uwnlp @allen_ai
With open models & 45M-paper datastores, it outperforms proprietary systems & match human experts.
Try out our demo!
We also introduce ꜱᴄʜᴏʟᴀʀQᴀʙᴇɴᴄʜ, a new large-scale multi-domain benchmark for scientific research synthesis, covering CS, Bio and Physics.

[Jia-Ying Lin @linekin]

原來早就有劇本

[( ͡° ͜ʖ ͡°) 卡珊德拉該練核心了8️⃣9️⃣6️⃣4️⃣ @balababada]

信了!

[Jia-Ying Lin @linekin]

@Inu_Natsume 不知道為什麼，都2024年了，第一個冒出來的念頭是「你們很勇敢」！加油！

[Evan Lin@LINE DevRel @Evan_Lin]

想說試試看用 #BingSearch 來幫忙做 #arxiv 五月份的 LLM 論文整理。效果很好

「總結這個月在 arxiv 發表關於 LLM 的新論文。請用 markdown 格式寫出」#chatgpt

[Jia-Ying Lin @linekin]

@Evan_Lin 為了找這個 prompt，翻了推主半年的推文~

[Alex Volkov @altryne]

Watching @karpathy presentation from today and taking twitter notes, come along for the ride:

If you're like only the practical tips, skip to #32

@karpathy starts with stages:
1 - Pre-training - months x thousands of GPUs
2, 3, 4 - Finetuning stages that take hours or days

1/

[Chunting Zhou @violet_zct]

How do you turn a language model into a chatbot without any user interactions?

We introduce LIMA: a LLaMa-based model fine-tuned on only 1,000 curated prompts and responses, which produces shockingly good responses.
* No user data
* No mode distillation
* No RLHF

[Thomas Wolf @Thom_Wolf]

Super nice to see so much excitation for open evaluation of large language model.

Currently 228 community-submitted models in the queue for being evaluated on the Hugging Face cluster's spare cycles and added to the leaderboard!

Check it out here: https://t.co/EOm1Drxd6N

[Julien Chaumond @julien_c]

Some people said that closed APIs were winning...

but we will never give up the fight for open source AI ⚔️⚔️

Today is a big day as we launch the first open source alternative to ChatGPT:

HuggingChat 💬

Powered by Open Assistant's latest model – the best open source chat model right now – and @huggingface Inference API.

Try it out now:

https://t.co/npBD1NRvQL

[elvis @omarsar0]

Not sure how I missed it, but this is a great overview of efficient NLP methods.

While models are scaled for performance, there is also a need to increase efficiency in modern NLP models. This survey paper covers methods and findings in efficient NLP.

https://t.co/lZ9dyX6OUb

[Manu Romero @mrm8488]

My next talk is a about the IT LLMs Zoo

[Andrej Karpathy @karpathy]

Random note on k-Nearest Neighbor lookups on embeddings: in my experience much better results can be obtained by training SVMs instead. Not too widely known.

Short example:
https://t.co/RXO9xiOmAB

Works because SVM ranking considers the unique aspects of your query w.r.t. data.

[Ali Ghodsi @alighodsi]

Free Dolly! Introducing the first *commercially viable*, open source, instruction-following LLM. Dolly 2.0 is available for commercial applications without having to pay for API access or sharing data with 3rd parties. https://t.co/HtRVSmArFU

[Bi-khim Hsiao 蕭美琴 @bikhim]

Welcome to New York!

[Jia-Ying Lin @linekin]

@annalu_tw ChatGPT 的用法，沒想到 ChatGPT 可以當引導的角色。

[Tsinghua KEG (THUDM) @thukeg]

ChatGLM-6B & ChatGLM!

ChatGLM-6B is an open CN&EN model w/ 6.2B paras (optimized for Chinese QA & dialogue for now). Trained for 1T tokens, SFT, Feedback Bootstrap, & RLHF.

w INT4 quantization, we can deploy on one 2080Ti card (6GB GPU mem required).

https://t.co/QpXWvLhTdU