Andrew Hojel

research @openai

[Andrew Hojel @AndrewHojel]

@gauri__gupta @NeoSigmaAI @RitvikKapila Congrats on the launch @RitvikKapila!

[Andrew Hojel @AndrewHojel]

Had a blast working on search capabilities for 5.3 Instant. Hopefully you notice that search responses feel more 🤌 

[OpenAI @OpenAI]

GPT-5.3 Instant gives you more accurate answers. When using web search, you also get:

- Sharper contextualization

- Better understanding of question subtext

- More consistent response tone within the chat

[Andrew Hojel @AndrewHojel]

eyooooo first launch at @OpenAI

[OpenAI @OpenAI]

Introducing shopping research, a new experience in ChatGPT that does the research to help you find the right products.

It’s everything you like about deep research but with an interactive interface to help you make smarter purchasing decisions.

[Andrew Hojel @AndrewHojel]

It’s wild watching @platonmazarakis add features to @PrismCoder using @PrismCoder on his phone.

[Platon Mazarakis @platonmazarakis]

Launching background agents and a mobile app for Claude code. Code from anywhere! 
@PrismCoder
Go to https://t.co/P9hdY8xHFD to join! To get instant access, like and reply “Prism codes”

[Andrew Hojel @AndrewHojel]

@platonmazarakis @PrismCoder prism codes

[Andrew Hojel @AndrewHojel]

🚀🚀

[Ritvik Kapila @ritvikkapila]

#1 trending on @huggingface letsgoooo!

@essential_ai 🥇

[Andrew Hojel @AndrewHojel]

@SinclairWang1 @essential_ai @FaZhou_998 We uploaded the revised version to arXiv, and it should be up in the next few days.

[Andrew Hojel @AndrewHojel]

@SinclairWang1 @essential_ai @FaZhou_998 Hey @sinclairwang1! Apologies, we definitely should include MegaMath-Web-Pro. Launching an experiment right now and will update the tables and corresponding section with the results. We think MegaMath rocks!

[Andrew Hojel @AndrewHojel]

@SinclairWang1 @essential_ai @FaZhou_998 If there are any datasets from MegaMath Web that are better representative of its performance before LLM rewriting, we are happy to update Table 3.

[Andrew Hojel @AndrewHojel]

@SinclairWang1 @essential_ai @FaZhou_998 We only report filtered web data as our goal is to purely measure the effects of different filtering methods to benchmark the performance of EAI-Taxonomy.

[Andrew Hojel @AndrewHojel]

@SinclairWang1 @essential_ai @FaZhou_998 Hey @SinclairWang1 and @FaZhou_998! We ran with MegaMath Web Pro and reported the (very strong) performance in Appendix A.7. We have also added a clear explanation that all the evaluated datasets are filtered web data without any LLM intervention.

[Andrew Hojel @AndrewHojel]

Check out what the Data Team at @essential_ai has been cooking! It's been a blast preparing this dataset and super excited to see what people use it for. Shoot me a DM with any questions or cool use cases.

[Essential AI @essential_ai]

[1/5]

🚀 Meet Essential-Web v1.0, a 24-trillion-token pre-training dataset with rich metadata built to effortlessly curate high-performing datasets across domains and use cases!

[Essential AI @essential_ai]

We are excited to announce Essential AI, founded by @ashvaswani and @nikiparmar09

https://t.co/pmd2ecSsZw

[niki parmar @nikiparmar09]

Thrilled to announce our company, https://t.co/eAn8liymKY 🚀
We are in an exciting era of human-computer collaboration evolving the way we will reason with, process and generate information.

At Essential AI, we are passionate on advancing capabilities in planning, reasoning, tool use and continual learning that will be critical to bridge the knowledge and skill gap between humans and computers.

[Ashish Vaswani @ashVaswani]

I'm thrilled to announce our company, @essential_ai . We believe that breakthroughs in AI will unlock the most profound tools for thought, advancing humanity's collective knowledge and capability.

https://t.co/unA2spJDDR

[Immanuel Trummer @ImmanuelTrummer]

🎉 Great news: our paper on #Evaporate, led by @simran_s_arora from @HazyResearch, was accepted at #PVLDB2023!
#Evaporate uses #LLMs to extract structured views from unstructured data.
📰 Paper: https://t.co/w6RDrvF0uM
💾 Code: https://t.co/EO0XB1S9dk
#GPT4 #DB #LanguageModel

[Jerry Liu @jerryjliu0]

LLMs can directly extract structured data (esp w/ Function API), but can be slow/expensive. 🤔

Instead: use LLMs to generate code, run code to extract data 💡

We now have code-based extraction in @llama_index - extract df’s from arbitrary text 🧑‍💻

https://t.co/Iq1SucKwp4

[Simran Arora @simran_s_arora]

LMs can be expensive for document processing. E.g., inference over the 55M Wiki pages costs >$100K (>$0.002/1k toks)💰 We propose a strategy that reduces inference cost by 110x and can even improve quality vs. running inference over each doc directly!
💻​ https://t.co/sDqvxSGyLE