Asha Vishwanathan (@ashavish) header
Asha Vishwanathan (@ashavish) profile picture

AI / Data Science / ML + Product + Startups , Artist, Sustainable Living, Blogger, https://teapawt.net/t.co/uPpOQiuNsz, https://teapawt.net/t.co/O34xslHXz9

Bangalore
Joined April 2021
Photo by Asha Vishwanathan (@ashavish)
Very good intiative in education. Definitely gives us pause to rethink our current education system
Here's a story of how the Bhagavad Gita led to us setting up an apprenticeship program. We at Comini, along with 3f.vc, are going to fund bright, passionate students and enable meaningful real-life learning across domains. PLEASE SHARE THIS WITH COLLEGE STUDENTS YOU KNOW 🙏 In effect: Cheaper, better, faster real-life learning from the real world. You can read the story here: betterschooling.in/collectio… Interested in apprenticeships or mentoring? Please fill this form: forms.gle/7N4iNwXZVAuQGC5P8 And here’s the story! 🧵 betterschooling.in/collectio…
1
32
Doing RAG on PDFs and other gnarly document formats is no walk in the park. Using markdowns in our ingestion pipeline has been a game-changer for many of our use cases — clean, simple, and surprisingly effective. verloop.substack.com/p/markd…
25
Asha Vishwanathan retweeted
We just received 2,500 job applications. Fewer than 100 filled a form with open-ended questions. About 15 went on to complete a reasonably simple real-world challenge. We are a nation with the cheapest internet and a billion internet users. Where are all the self-directed learners? The eclectic Ekalavyas? PS: Here's the link with the form and challenge comini.in/hiring_soft_dev
3
3
8
639
Cool stuff ! This sounds like LLM powered RPAs anthropic.com/news/3-5-model…
1
22
Jaw droppingly good !
Here’s an early preview of ElevenLabs Music. All of the songs in this thread were generated from a single text prompt with no edits. Title: It Started to Sing Style: “Pop pop-rock, country, top charts song.”
2
66
Asha Vishwanathan retweeted
You can find the recording of this talk by @ashavish here. It is a must-watch for anyone looking to build production-grade features using LLMs. saasengineering.substack.com…
1
1
1
118
This looks like a really neat idea !
LLMs as Optimizers This is a really neat idea. This new paper from Google DeepMind proposes an approach where the optimization problem is described in natural language. An LLM is then instructed to iteratively generate new solutions based on the defined problem and previously found solutions. It was first tested on linear regression and the traveling salesman problem. Leveraging LLMs with simple prompting match or surpass hand-designed heuristic algorithms. This shows good potential for using LLMs as optimizers. The idea is then applied to prompt optimization that aims to maximize task accuracy on different tasks like math word problem-solving. The first piece of the proposed meta-prompt takes in previously generated prompts along with corresponding training accuracies. The second piece includes the optimization problem description with samples obtained from a training set representing the task. At each optimization step, the goal is to generate new prompts that increase test accuracy based on the trajectory of previously generated prompts. The optimized prompts outperform human-designed prompts on GSM8K and Big-Bench Hard, sometimes by over 50%! For math word problem solving, one of the most effective instructions found begins with "Take a deep breath and work on this problem step-by-step". arxiv.org/abs/2309.03409
2
286
This is awesome 🔥. Llama 2 seems to be doing better on the benchmarks for 7B models as well ! ai.meta.com/llama/
We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️ bit.ly/3Dh9hNp
2
115
This is some crazy speed ! OpenAI just announced Functions today
🚨🤖New Agent Release🤖🚨 We can @OpenAI's new function parameter to create a new type of agent (`openai-functions`) now available in Python and JS Links to documentation a thread on what went into it below 👇
86
Good stuff . Vicuna is definitely coming on top. We found 13b unquantized model outputs are quite good for fact based outputs, but dont do so great for "creative" outputs in comparison to chatGPT. Latency however is still an issue.
There are so many chatbots nowadays, it’s hard to keep up! To help out, we made an open source tool for automatic comparison of chatbots, and created a report on LLaMa, Alpaca, Vicuna, ChatGPT, Cohere, etc.! Report: github.com/zeno-ml/zeno-buil… Browser: zeno-ml-chatbot-report.hf.sp… 🧵⬇️
70
Asha Vishwanathan retweeted
Pause and think for a second, 689%! LLMs will change the way industry manages customer support.
India + Philippines BPO story is over; LLMs can now consistently deliver better L1 and L2 ticket outcomes than most contact center agents.
1
7
1
43
13,072
Asha Vishwanathan retweeted
CBSE board exam admit card now has a mention of ChatGPT 😳
1
1
1
643
Was awesome to present our paper - "Multi tenant optimization for few shot talk oriented FAQ retrieval" for Industry track at EMNLP 2022 ! Thanks to all for stopping by at our poster session ! @rajeevuwarrier @gauthamsuresh09 @LazyLearner_ #EMNLP2022
1
1
12
*Correction - Multi tenant optimization for few shot task oriented FAQ retrieval
1
Thrilled to have our paper on "Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ Retrieval" accepted to EMNLP 2022 Industry Track !!! Preprint coming soon ! #EMNLP2022 @rajeevuwarrier @gauthamsuresh09 @LazyLearner_
This is so amazing ! <3
An exciting day for cohere.for.ai! We believe in changing where, how, and by whom research is done. Today we launch our Scholars Program — an opportunity to work with some of the best researchers in the world. Your journey starts here. txt.cohere.ai/introducing-th…
1
Mind blowing !
"Voyage through Time" is my first artpiece using #stablediffusion and I am blown away with the possibilities... We're crossing a threshold where generative AI is no longer just about novel aesthetics, but evolving into an amazing tool to build powerful, human-centered narratives
1
Asha Vishwanathan retweeted
10 lessons I learned from a brilliant software engineer. For over ten years, I shared a keyboard with him, and here are the things that stuck with me: 1 of 11
107
1,165
73
4,125
Asha Vishwanathan retweeted
Cog is Docker for machine learning. It lets you package your machine learning model in a standard, production-ready container. We’ve been using it internally for Replicate, and now it's ready to use for your own deployments. github.com/replicate/cog
7
105
10
547
Excited to be speaking at WiDS conference on April 9 ! I will be speaking on "Unravelling the machine learning behind Conversational AI" #WiDS2022 @iimb_official @WiDS_Worldwide
This Post is from an account that no longer exists. Learn more
4