Raunak (@raunakdoesdev) / X

Raunak

1,565 posts

Raunak

@raunakdoesdev

I’m into open science, elegant software architecture, and well-crafted interfaces. Building reducto.ai

San Diego, California

Joined July 2017

Pinned
Raunak
@raunakdoesdev
Oct 14, 2025
Big milestone for Reducto: we’ve raised a $75M Series B led by a16z, bringing our total funding to $108M. Since our launch, we’ve been obsessed with pushing the limits of what’s possible when AI meets the real-world messiness of documents. We’ve now processed 1B+ pages, nearly
61K
Raunak
@raunakdoesdev
Jun 17, 2023
A recent work from @iddo claimed GPT4 can score 100% on MIT's EECS curriculum with the right prompting. My friends and I were excited to read the analysis behind such a feat, but after digging deeper, what we found left us surprised and disappointed. dub.sh/gptsucksatmit 🧵
No, GPT4 can’t ace MIT | Notion
From flower-nutria-41d.notion.site
3.5M
Raunak
@raunakdoesdev
Aug 30, 2025
claude code makes new computer setup so nice
301K
Raunak
@raunakdoesdev
Sep 8, 2023
I just built an infinite memory system for LLM chats: Remembrall. Add a UID to your OpenAI call and I'll manage inserting past chat history into the context window with < 100ms latency. 2 lines of code to integrate. @helicone_ai style monitoring for free. DM for beta access.
555K
Raunak
@raunakdoesdev
Jun 18, 2023
Update: we've started replicating their experiments directly with GPT4 calls, and somehow it only gets worse. We've finished running zero-shot GPT 4 on the dataset, and after hand grading the first 30% of the dataset, the results don't seem to match the paper. 🧵
Raunak
@raunakdoesdev
Jun 17, 2023
A recent work from @iddo claimed GPT4 can score 100% on MIT's EECS curriculum with the right prompting. My friends and I were excited to read the analysis behind such a feat, but after digging deeper, what we found left us surprised and disappointed. dub.sh/gptsucksatmit 🧵
652K
Raunak
@raunakdoesdev
Jun 17, 2023
Replying to @raunakdoesdev
We hope our work encourages skepticism for GPT as eval ground truth, and encourages folk to look a little deeper into preprint papers before sharing. Much thanks to @NeilDeshmukh and @David_Koplow for working w/ me on this and @willwjack for the review.
No, GPT4 can’t ace MIT | Notion
From flower-nutria-41d.notion.site
92K
Raunak
@raunakdoesdev
Jun 17, 2023
Replying to @raunakdoesdev
Well... it didn't. The authors evaluation uses GPT 4 to score itself, and continues to prompt over and over until the correct answer is reached. This is analogous to someone with the answer sheet telling the student if they’ve gotten the answer right until they do. (2/4)
229K
Raunak
@raunakdoesdev
Jul 25, 2023
105 ML papers were published on @arxiv today. It's getting harder and harder to keep up with the latest ML research. Today we're making it a bit easier with a free LLM powered app that goes from PDFs to beautiful markdown summaries in seconds. Try it yourself below 👇 (1/4)
173K
Raunak
@raunakdoesdev
Jun 17, 2023
Replying to @raunakdoesdev
That's not all. In our analysis of the few-shot prompts, we found significant leakage and duplication in the uploaded dataset, such that full answers were being provided directly to GPT 4 within the prompt for it to parrot out as its own. (3/4)
102K
Raunak
@raunakdoesdev
Jul 31, 2023
🏆 We* won 1st place at the @AnthropicAI hackathon today with ClaudeScholar, a research assistant for science that can synthesize data, extract insights, and automate scientific workflows. Try it @ claudescholar.com * @AbrahamAdit, @johnyang100, @tinahhong 🧵 (1/5)
00:00
109K
Raunak
@raunakdoesdev
Mar 16, 2024
🤯 crazy exchange on @modal_labs slack between @cognition_labs 's Devin & modal's support team
1M
Raunak
@raunakdoesdev
Jun 24, 2023
FINAL UPDATE: On June 24th, Armando Solar-Lezama (Professor in EECS and COO/Associate Director of CSAIL, MIT), Tonio Buonassisi (Professor of Mechanical Engineering, MIT), and Yoon Kim (Assistant Professor in EECS and CSAIL, MIT) released a public statement regarding the paper.
Raunak
@raunakdoesdev
Jun 17, 2023
A recent work from @iddo claimed GPT4 can score 100% on MIT's EECS curriculum with the right prompting. My friends and I were excited to read the analysis behind such a feat, but after digging deeper, what we found left us surprised and disappointed. dub.sh/gptsucksatmit 🧵
775K
Raunak
@raunakdoesdev
Jun 17, 2023
Replying to @raunakdoesdev
The released test set on Github is chockfull of impossible to solve problems. There are lots of questions referring to non-existent diagrams and missing contextual information. So how did GPT solve it? (1/4)
93K
Raunak
@raunakdoesdev
Aug 10, 2023
Google's guide for building an object detector is 30 pages long. LLMs can do multivariable calculus. It shouldn't be this hard for machines to find an apple in a tree. Today, I made a way to go from unlabeled images to a deployed object detection model in 5 minutes. 🧵 (1/3)
138K