shyamal @shyamalanadkat Twitter profile

Pinned Tweet

shyamal

@shyamalanadkat

6 months

love wins. humanity wins.

3

5

114

Last Seen Profiles

@Helen_Barnard

@LiLYPSE

@balerostyle

@CEN_HQ

@YR5Z5P8T6iq6oqu

@RaceClicker

@Unifrance

@Dierelc

@OrbeonProtocol

@Valerie21824390

@hmirfanullah

@YakisobaDeAtum

@eusouwillbank

@SaveTheStudent

@suicaa_melonn31

@8dTOnbFSbDYFqx9

@mt165

@Marioistheking

@Smash_OCE

@YoMPBigRed

@kazumitico

@Syndica_io

@OHS_GoPanthers

@_Dametualma666_

@Kingmorena

@sinbadfps

@ARMENEXPO

@Gizmyyy

@cosmxxian

@pedro_vilchesSR

@Lifeuwrestling

@Cr1tdota

@ilikeicecoffee

@ZusuruMiya

@Coach_CBooth

@Stxticcss

shyamal

@shyamalanadkat

6 months

🩶

Sam Altman

@sama

6 months

i love the openai team so much

5K

4K

73K

7

19

796

shyamal

@shyamalanadkat

3 months

on my recent visit to india, i met a super sharp 19-year-old student from a remote town in gujarat, india. surprisingly, he traveled for 11 hrs each way to meet me for a 3 hr long discussion about agi, consciousness, creativity, anomalies in our approach to RL, spatial computing,…

23

32

631

shyamal

@shyamalanadkat

1 year

exploring k-means clustering on the Iris dataset using code interpreter chatGPT plugin ✨

22

95

561

shyamal

@shyamalanadkat

6 months

OpenAI is nothing without its people

12

29

530

shyamal

@shyamalanadkat

5 months

grateful as ever ❤️

4

8

533

shyamal

@shyamalanadkat

1 year

we also dropped the chatgpt retrieval plugin that enables semantic search and retrieval of personal or organizational documents. s/o to @IsaFDev .

GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily find...

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language. - openai/chatgpt-retrieval-plugin

github.com

11

57

416

shyamal

@shyamalanadkat

4 months

here are some basic → advanced strategies that I see for optimizing RAG implementations these days: basic 1. using effective prompt eng, templating, and conditioning. eg: “given the context information and no prior knowledge, answer the query..” etc. ok, we've all done some…

7

46

358

shyamal

@shyamalanadkat

6 months

today, we’re releasing the Assistants API, our first step towards helping developers build agent-like experiences within their own applications. inspire. build. dream.

OpenAI Platform

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

platform.openai.com

6

25

326

shyamal

@shyamalanadkat

1 year

The LLM landscape is increasingly starting to look something like this: (1) Model layer (e.g gpt3, cohere)(2) API bindings for access (e.g openai-python) (3) Infra layer for prompt chaining/model switching (e.g., @LangChainAI , @dust4ai ) (4) Next gen AI-first apps. what's missing?

13

19

271

shyamal

@shyamalanadkat

5 months

shipping AI without calling it AI is underappreciated. it brings back focus on users and value; no hype, just utility that users gradually rely on. often the best solutions hide complexity behind simple interfaces.

20

34

274

shyamal

@shyamalanadkat

1 year

updated guide for Q&A with GPT and embeddings-based search OR "how do I integrate with ChatGPT using my own custom data" - ; s/o to the amazing @sandersted

openai-cookbook/examples/Question_answering_using_embeddings.ipynb at main · openai/openai-cookbook

Examples and guides for using the OpenAI API. Contribute to openai/openai-cookbook development by creating an account on GitHub.

github.com

5

28

259

shyamal

@shyamalanadkat

2 months

hot take: RAG has become unnecessarily too complex and way too commercialized/productized; we should really work on simplifying it and build cleaner, better abstractions.

30

11

256

shyamal

@shyamalanadkat

1 year

new guide for building a tool-using agent with LangChain OR "how do I augment ChatGPT with my own custom data and external tools/APIs" - ; s/o to @colintjarvis

3

56

247

shyamal

@shyamalanadkat

6 months

what a week to be oncall 😅 👊🏼

19

1

225

shyamal

@shyamalanadkat

10 months

some of the most talented human agents hacking on AI agents at the @scale_AI genAI hackathon. i love san francisco!

11

12

218

shyamal

@shyamalanadkat

4 months

recently got a call from a cousin who said the GujRERA (gujarat real estate regulatory authority) portal was taking about 20-30 seconds to load when he was trying to get a simple question answered. so, i quickly prototyped an openai + @embedchain powered assistant that provides…

12

22

203

shyamal

@shyamalanadkat

6 months

@OpenAI huge respect for team that keeps shipping

3

1

193

shyamal

@shyamalanadkat

1 year

LLMOps is young but growing fast; key areas include: (1) prompt management & evals (chaining, audit, a/b testing, etc) (2) simplifying finetuning & embeddings (3) agent integration/action execution (interfacing w/ external world) (4) analytics & observability - cost, latency, etc

4

11

188

shyamal

@shyamalanadkat

1 year

few verticals & companies working with LLMs i’m excited about: 1/ legal tech startup @LexionAi is using GPT-3 to help lawyers write summaries and suggest edits.

Lexion Announces GPT-Based AI Contract Assist - Lexion

Lexion's AI Contract Assist brings GPT technology to Word for to generate clause language and suggest redlines

www.lexion.ai

5

24

164

shyamal

@shyamalanadkat

6 months

we’ll be so so back.

7

5

153

shyamal

@shyamalanadkat

1 year

Key moats for LLM/AI-first applications, in order of importance: (1) Proprietary data and fine-tuning (2) Great UX + one that instills a sense of trust and reliability (3) Distribution and GTM (4) Network effects and community (5) Breadth and depth of integrations What else?

10

20

153

shyamal

@shyamalanadkat

1 year

at the chatgpt API hackathon today in SF organized by @rachel_l_woods and @nonmayorpete in ~3 days. the energy is off the charts with over 200+ in attendance. can’t wait to see the demos 🔥

1

6

132

shyamal

@shyamalanadkat

7 months

i don't say this enough but i love openai. it's absolutely been the highlight of a lifetime to work here, drive the kind of positive impact, help shepherd the technology to help humanity and progress towards agi, and collaborate with some of the most talented, hardworking,…

6

7

125

shyamal

@shyamalanadkat

1 year

silicon valley at its best at @scale_AI ’s generative AI hackathon this saturday in SF. s/o to @russelljkaplan and his team for making this happen.

5

15

114

shyamal

@shyamalanadkat

6 months

OPENAI OPENAI OPENAI OPENAI DEVDAY DEVDAY DEVDAY DEVDAY OPENAI OPENAI OPENAI DEVDAY DEVDAY DEVDAY OPENAI OPENAI OPENAI OPENAI DEVDAY DEVDAY

5

9

116

shyamal

@shyamalanadkat

1 year

Check out OpenAI's new Production Best Practices guide! It covers a range of topics to help developers transition from prototype to production. Let us know what you think!

OpenAI Platform

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

platform.openai.com

3

22

113

shyamal

@shyamalanadkat

5 months

aligned ❤️

Greg Brockman

@gdb

5 months

❤️

503

254

9K

1

3

110

shyamal

@shyamalanadkat

6 months

@OfficialLoganK @OpenAI openai is nothing without its customers and developers

2

5

111

shyamal

@shyamalanadkat

1 year

"prompting LLMs is almost like subtractive sculpting; each additional word in the prompt eliminates some possible worlds and defines the task more clearly" - @goodside

3

12

109

shyamal

@shyamalanadkat

10 months

1/ practical tactics to reduce LLMs from hallucinating🧵: during training, LLMs auto-regressively predict the next token in a sequence. despite their impressive performance, LLMs sometimes generate outputs that are factually incorrect/ nonsensical, known as hallucinations.

4

14

105

shyamal

@shyamalanadkat

6 months

committed to the team and the mission 🫡

7

2

98

shyamal

@shyamalanadkat

6 months

At OpenAI DevDay, @sherwinwu and I had the pleasure of giving a talk on 'The New Stack and Ops for AI', where we discussed a new framework to navigate the unique considerations for scaling non-deterministic apps from prototype to production. if you couldn't join us live, you can…

5

9

95

shyamal

@shyamalanadkat

6 months

@sama we love you sam ♥️

0

91

shyamal

@shyamalanadkat

1 year

next couple of years will present a steep tech curve - AI-first companies disrupting entire industries with beautiful language interfaces, LLM apps, and novel interaction paradigms resulting in 10x productivity/efficiency gains & driving the marginal cost of knowledge work down.

6

15

86

shyamal

@shyamalanadkat

11 months

sharing some insights that can help founders and builders navigate the landscape, enabling AI-enabled and AI-native products/experiences that can amplify humanity:

frontiers, startups, 2023++

The past year has been both wild and very empowering. Wild because of an apparent fast take off in AI, and empowering because of lots of love for language user interfaces and support from the...

www.linkedin.com

1

11

79

shyamal

@shyamalanadkat

1 year

Thin layers around LLM APIs aren't enough to gain a competitive edge in AI-first apps. To win, you need deep integrations and optimized workflows that solve real problems with the scalability and efficiency that wasn't possible pre-GPT.

3

12

79

shyamal

@shyamalanadkat

1 year

@alliekmiller Every AI person I know is beyond excited and is in “building mode”.

5

78

shyamal

@shyamalanadkat

1 year

new guide on OpenAI API rate limits and how developers can batch request / handle retries: , s/o to @OfficialLoganK

OpenAI Platform

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

platform.openai.com

1

14

78

shyamal

@shyamalanadkat

1 year

excited about the potential for LLMOps & LLM tooling (things like prompt testing & experimentation at scale, vector db & ops, data to embeddings, no code, etc). with foundational models in place, tooling & integrations will make them more reliable & easier to operationalize.

6

8

78

shyamal

@shyamalanadkat

6 months

"Getting fired from Apple was the best thing that could have ever happened to me. The heaviness of being successful was replaced by the lightness of being a beginner again, less sure about everything. It freed me to enter one of the most creative periods of my life." - Steve…

3

5

75

shyamal

@shyamalanadkat

28 days

looking to connect with a few IITians to discuss the current state of education in india. if you're an IIT student / alum, would love to hear your insights. feel free to DM or reply below.

28

9

75

shyamal

@shyamalanadkat

26 days

how to use gpt4 turbo vision with function calling -

1

15

74

shyamal

@shyamalanadkat

6 months

bad fever dream

5

2

70

shyamal

@shyamalanadkat

11 months

0/ compiling some openai function calling API tips/pointers from few developers:

1

16

70

shyamal

@shyamalanadkat

1 year

how to format inputs to ChatGPT models - . s/o to @sandersted

4

8

70

shyamal

@shyamalanadkat

1 year

Creating a ChatGPT plugin in 3 steps: 1/ build an API 2/ document the API in the OpenAPI yaml or JSON format 3/ create a JSON manifest file that will define relevant metadata for the plugin example todo list plugin:

OpenAI Platform

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

platform.openai.com

2

13

67

shyamal

@shyamalanadkat

6 months

@mengxilu im on h1b and i signed :)

3

1

62

shyamal

@shyamalanadkat

1 year

i love openai, and everything we stand for, the people, the tech, the problems we're solving, the impact we're having, and staying committed to learning & growing along the way.

1

3

64

shyamal

@shyamalanadkat

4 months

Memes, Brainstorm, Knowledge, Identity

Aravind Srinivas

@AravSrinivas

4 months

Memes, Brainstorm, Knowledge

86

89

2K

2

6

61

shyamal

@shyamalanadkat

6 months

👑

Sam Altman

@sama

6 months

first and last time i ever wear one of these

4K

6K

99K

2

60

shyamal

@shyamalanadkat

3 months

obsessed with AI startups accelerating knowledge workers rn.

7

3

60

shyamal

@shyamalanadkat

10 months

@paulg the dealer's profits rely on the liquidity and turnover of the artwork, not on its potential long-term appreciation; it’s not necessarily about the highest future value, but the optimization of transaction frequency and profitability

2

58

shyamal

@shyamalanadkat

1 year

prompt engineering is such a fascinating & creative field that combines NLU, domain knowledge, and human intuition to elicit the best possible responses from LLMs. it will evolve with LLMs, requiring new methods and tools to harness their full potential.

3

7

57

shyamal

@shyamalanadkat

22 days

you really don't know/understand what hypergrowth feels like unless you're part of it day in, day out. the intensity and pace are hard to grasp from the outside.

3

59

shyamal

@shyamalanadkat

7 days

focus on doing a few things exceptionally well and be committed to those.

0

6

62

shyamal

@shyamalanadkat

28 days

i love cursor. absolutely great team and delightful product.

Cursor

@cursor_ai

29 days

Cursor users can now use the new gpt-4-turbo model. We’ve observed improved reasoning on complex tasks. Example comparison between gpt-4-1106 and the new gpt-4-turbo below:

24

53

542

2

4

58

shyamal

@shyamalanadkat

6 months

moved from chrome to arc. swapped vscode for cursor. shifting from docs to notion. thanks for shipping, innovating, and reshaping my stack @browsercompany @anysphere and @NotionHQ

7

3

53

shyamal

@shyamalanadkat

5 months

best day ever. truly blessed to be alive.

1

0

52

shyamal

@shyamalanadkat

1 year

AI-first apps will transform how we work & collaborate over the next 5 years, making knowledge work and intelligence more accessible & affordable. Note-taking & copyrighting are just the beginnings. New interfaces, CRMs, tax prep copilot, research assistants are all fair game.

3

8

53

shyamal

@shyamalanadkat

6 months

700+ and counting

Lilian Weng

@lilianweng

6 months

About 650 / 770 signed at this moment. As people start waking up, more will come. All the efforts started after 1:30 AM, 500+ within two hours and all of this after 2 crazy days with very little sleep.

161

609

5K

0

2

52

shyamal

@shyamalanadkat

1 year

ChatGPT plus is here -

5

3

51

shyamal

@shyamalanadkat

5 months

the ‘low key research preview’ over the past year evolved from a toy to a tool, and now to a capability that millions depend on. happy birthday, @ChatGPTapp ; we are just getting started.

Sam Altman

@sama

5 months

a year ago tonight we were probably just sitting around the office putting the finishing touches on chatgpt before the next morning’s launch. what a year it’s been…

2K

3K

45K

0

2

47

shyamal

@shyamalanadkat

5 months

logprobs are back! you can use it as a likelihood function or get confidence scores on classification tasks, enabling more interpretability in outputs.

OpenAI Developers

@OpenAIDevs

5 months

By popular demand, log probabilities are now in the Chat Completions API! With logprobs for top output tokens, you can build features such as better autocomplete, classification, keyword suggestion, or assess the model’s confidence in its predictions.

65

199

2K

4

1

46

shyamal

@shyamalanadkat

1 year

the most important thing I have realized this year: life is truly and should be centered around people you love and people you serve. everything else is nice to have.

3

47

shyamal

@shyamalanadkat

1 year

recursive prompt chaining is a powerful tool; leveraging LLMs to evaluate your completion outputs and further assessing those evaluations lets you fine tune results for maximum efficacy and robustness across many use-cases.

2

3

44

shyamal

@shyamalanadkat

6 months

huge thank you to the entire openai leadership team for making this happen🩵 one team, one mission.

Greg Brockman

@gdb

6 months

we are so back

2K

4K

52K

0

43

shyamal

@shyamalanadkat

3 months

hello, sora

OpenAI

@OpenAI

3 months

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. Prompt: “Beautiful, snowy…

10K

33K

141K

3

1

43

shyamal

@shyamalanadkat

1 year

is now 🙌🏻

1

3

43

shyamal

@shyamalanadkat

1 year

the @full_stack_dl LLM Bootcamp may be the best event taking place this weekend in the bay area. kudos to everyone involved in making it happen!

0

4

43

shyamal

@shyamalanadkat

16 days

cheap, abundant, and customizable intelligence at scale has to be this year's theme.

1

5

43

shyamal

@shyamalanadkat

4 months

the trojan horse for AI is not anthropomorphism but intelligence augmentation. rather than building bots/integrations that aim to pass as human, the best founders will create tools that feel like natural extensions of our own abilities. the real goal is leveraging computation to…

3

41

shyamal

@shyamalanadkat

4 months

i missed this

4

1

41

shyamal

@shyamalanadkat

1 year

some of the most valuable AI first companies will create entirely new UX paradigms and interaction models powered by elegant natural language interfaces

3

6

40

shyamal

@shyamalanadkat

1 year

there we go - 👏

2

3

38

shyamal

@shyamalanadkat

11 months

outlining some practical measures for limiting LLM hallucinations in this post -

Reducing Large Language Model Hallucinations: Practical Tactics

Let’s first understand what hallucinations (aka “fabricated information”) are in the context of large language models and why they happen. During the training process of large language models/GPTs,...

shyamal.me

1

11

39

shyamal

@shyamalanadkat

1 year

@sama life is truly and should be centered around people you love and people you serve. everything else is nice to have.

1

3

37

shyamal

@shyamalanadkat

24 days

can't wait to see a world where we don't have to worry about some llm api rate limits, incremental costs, and inference latencies, where we continue to drive down the cost of compute + intelligence. abundance will unlock tremendous value and adoption, even with current…

0

2

39

shyamal

@shyamalanadkat

6 months

agreed. shipping stuff at openai is so inspiring, exciting and brings the best out of silicon valley

Logan Kilpatrick

@OfficialLoganK

6 months

I don’t think people comprehend how much work goes into OpenAI launches, it’s exhausting and yet so inspiring.

50

14

501

2

0

37

shyamal

@shyamalanadkat

11 months

as the doubts about creating a moat with LLMs fade, we recognize that the platform does not guarantee equality. it's like gaming consoles being around for decades, yet game developers are still competing in creating the most immersive games. this highlights the importance of…

2

8

35

shyamal

@shyamalanadkat

1 year

gpt4 can act as an effective discriminator/verifier to gpt 3.5 outputs. for eg - by asking 3.5 to answer a question and then asking gpt4 to verify the validity/truthfulness of the answer given the context, we can achieve a higher level of confidence.

3

4

33

shyamal

@shyamalanadkat

1 year

The three stages of LLM developments: 1.0: Capable of generating original text and reasoning about it. 2.0: Able to evolve, refine its output, and acquire new abilities to act rationally. 3.0+: Can design its own actions/capabilities to interact with the external world

4

1

35

shyamal

@shyamalanadkat

11 days

abundance mindset should be a birthright

1

3

35

shyamal

@shyamalanadkat

11 months

exciting updates - function calling capability in the api with updated & more steerable versions of gpt-4 and gpt-3.5-turbo - 16k context version of gpt-3.5-turbo - 75% cost reduction on embeddings api - 25% cost reduction on input tokens for gpt-3.5-turbo

Function calling and other API updates

We’re announcing updates including more steerable API models, function calling capabilities, longer context, and lower prices.

openai.com

3

4

34

shyamal

@shyamalanadkat

10 months

@abacaj very satisfying for some reason / almost like therapy

0

33

shyamal

@shyamalanadkat

3 months

your users don’t have to know you’re building with LLMs just like they don’t have to know you’re building with javascript; intelligence is value. and necessary, not just an accessory.

2

3

34

shyamal

@shyamalanadkat

10 months

we’ve come a long way. code interpreter available to all chatGPT plus users over the next week - a preview into the future of work.

shyamal

@shyamalanadkat

1 year

exploring k-means clustering on the Iris dataset using code interpreter chatGPT plugin ✨

22

95

561

1

4

33

shyamal

@shyamalanadkat

1 year

you only get a few shots at building your life’s work

1

4

31

shyamal

@shyamalanadkat

1 year

chatgpt plus and gpt4 are now available to everyone in India. this is a huge milestone for us and it’s going to be really exciting to see the possibilities 🇮🇳 ❤️

1

4

32

shyamal

@shyamalanadkat

1 year

few areas within LLM space I’m personally excited about: (1) horizontals - tooling/infra, no/low code, finetuning, prompt chaining + retrieval, actions, experimentation frameworks (2) verticals - copilot for x, AI-native CRMs, edtech, health, enforcement/safety. Lots to explore!

0

3

30

shyamal

@shyamalanadkat

6 months

'Agent-based computing (ABC) is likely to be the next significant breakthrough in software development.' (Sargent, 1992)

2

30

shyamal

@shyamalanadkat

3 months

we imagined and created language as our key connection and communication tool. within centuries, we built things that understand and simulate our language and senses, opening portals to new interaction forms and essentially experiencing what might feel like magic. now language…

2

30

shyamal

@shyamalanadkat

8 months

gpt-3.5-turbo-instruct is out. it’s trained similarly to previous instruct models such as the text-davinci series while maintaining the same speed as our turbo models.

4

2

30

shyamal

@shyamalanadkat

6 months

wishing the best for humanity’s prosperity, compassion, happiness, and wisdom. happy diwali to everyone 🪔

3

0

30

shyamal

@shyamalanadkat

9 months

fine-tuning for gpt-3.5 is here!

OpenAI

@OpenAI

9 months

We've just launched fine-tuning for GPT-3.5 Turbo! Fine-tuning lets you train the model on your company's data and run it at scale. Early tests have shown that fine-tuned GPT-3.5 Turbo can match or exceed GPT-4 on narrow tasks:

406

2K

8K

2

30

shyamal

@shyamalanadkat

6 months

time to build. Lfg!!

Sam Altman

@sama

6 months

i love openai, and everything i’ve done over the past few days has been in service of keeping this team and its mission together. when i decided to join msft on sun evening, it was clear that was the best path for me and the team. with the new board and w satya’s support, i’m…

5K

8K

75K

0

1

29

shyamal

@shyamalanadkat

1 month

We’re adding new features to help developers have more control over fine-tuning and announcing new ways to build custom models with OpenAI.

Introducing improvements to the fine-tuning API and expanding our custom models program

We’re adding new features to help developers have more control over fine-tuning and announcing new ways to build custom models with OpenAI.

openai.com

0

3

30

shyamal

@shyamalanadkat

3 months

mankind in transition

0

5

28

shyamal

@shyamalanadkat

9 months

too soon?

0

26

shyamal

@shyamalanadkat

23 days

“You will be paid for your creativity and ability to get things done with computers—not for esoteric knowledge of programming languages”

Amjad Masad

@amasad

23 days

My view is that it’s probably the best time to learn coding because you will need less of it and produce increasingly more magic. Eventually “coding” will almost entirely be natural language, but you will still be programming. You will be paid for your creativity and ability to…

25

64

523

0

3

28