Diwank Singh @diwanksingh

GPT whisperer. Serial dropout. Thiel fellow. Building AI agents @julep_ai. Dog father. diwank.name SF Joined October 2008

Tweets

2K
Followers

827
Following

953
Likes

760

Diwank Singh @diwanksingh

5 days ago

Hello #SFTechWeek 🙌🏎️

0 0 2 52 0

Diwank Singh @diwanksingh

a week ago

ai coding can be summed up in one word: rabbit holes

1 0 3 140 0

Sebastien Bubeck @SebastienBubeck

a month ago

Claim: gpt-5-pro can prove new interesting mathematics. Proof: I took a convex optimization paper with a clean open problem in it and asked gpt-5-pro to work on it. It proved a better bound than what is in the paper, and I checked the proof it's correct. Details below.

289 1K 8K 6.8M 3K

Download Image

Diwank Singh @diwanksingh

a month ago

we are github-trendy again! B-) github.com/julep-ai/julep

0 0 4 132 0

Diwank Singh @diwanksingh

2 months ago

i wanted o4 kinda feels like a cliffhanger to have o4-mini but not have o4.

0 0 2 151 0

Ishita Jindal @IshitaJindal17

2 months ago

Stop building AI agents from scratch. we just shipped 15 plug-and-play templates to build agents: - Browser Agent (scrapes anything) - Hook Generator (viral content) - Reel creator (based on current trends) + 12 more 🧵

2 3 18 1K 10

Om Bhardwaj @Ombhardwajj

2 months ago

@julep_ai @diwanksingh @lossfunk Attended this talk yesterday really insightful! Reading @diwanksingh’s blog beforehand probably helped me get even more out of it. 😀 The most sacrosanct rule: human writes the test 🫡 Coincidentally bumped into him today at The Fifth Elephant too!

0 2 5 184 0

Julep AI @julep_ai

2 months ago

Our co-founder @diwanksingh is speaking at @lossfunk tomorrow on Shipping Code 10X faster with Claude Code. Register below to join virtually or in-person 👇

2 2 22 2K 1

Diwank Singh @diwanksingh

3 months ago

my claude-code just threw a fit... > ● Now I'm confused. The environment variable evaluates to True in both contexts, but the tests are still being skipped with the message that it's not 'true'. Aborting.

0 0 3 305 0

Simon Willison @simonw

3 months ago

Forget em dashes, "game changer" is the real giveaway for LLM generated text (especially for bots on here)

195 32 2K 166K 155

Diwank Singh @diwanksingh

3 months ago

New post! open.substack.com/pub/relativity…

1 0 4 237 1

Download Image

Nicolas Hery @nicolas_hery

3 months ago

Some good practical tips from @diwanksingh on using agents like Claude Code more effectively: diwank.space/working-with-d… I appreciate folks sharing their workflows like this, especially for those of us who use AI but don't have much time to experiment.

1 1 4 172 0

Julep AI @julep_ai

3 months ago

excited to share that @julep is one of the 17 startups chosen for @Meta’s Llama Startup Program! honored to stand alongside an elite cohort and keep pushing open-source AI forward. Thanks Meta—let’s build! 🦙🚀

AI at Meta @AIatMeta

3 months ago

34 36 171 37K 26

Download Image

0 2 6 590 0

logx @LOGESHRAMESH4

4 months ago

@diwanksingh Very very very good

0 1 2 135 0

Changelog @changelog

4 months ago

This week's Changelog News! changelog.news/148

0 2 5 1K 3

Download Image

Aditya Babbar @xAditya

4 months ago

This is an excellent write-up. Some great tips and best practices on how to do AI-assisted product development (using Claude).

Diwank Singh @diwanksingh

4 months ago

This is an excellent write-up. Some great tips and best practices on how to do AI-assisted product development (using Claude).

4 4 11 1K 2

Download Image

1 1 2 233 0

Rui @Logreg_n_coffee

4 months ago

Love the clear instructions given to LLM. Thanks for this post! Very insightful!

Diwank Singh @diwanksingh

4 months ago

Love the clear instructions given to LLM. Thanks for this post! Very insightful!

4 4 11 1K 2

Download Image

1 1 1 267 0

Subba Reddy @PostPCEra

4 months ago

@paraschopra @lossfunk @diwanksingh good presentation on theoretical foundations of building agents. I found these two frameworks helpful for building Agentic systems. 1/ https://github. com/agno-agi/agno > Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning. 2/ crewAI

0 1 1 276 0

vedant @vedantbhatt018

4 months ago

Just finished watching this amazing talk by @diwanksingh on how to build AI Agents effectively. The 8 factors provide a definite idea about AI Agents. I had already built Agents in the past but haven't focused on Traces(8th factor). This will definitely help me debug easily.