Very excited to finally share OpenAI's "deep research" model, which achieves twice the score of o3-mini on Humanity's Last Exam, and can even perform some tasks that would take PhD experts 10+ hours to do! A few thoughts on the implications: Deep research can be seen as a new
LLMS
-
OpenAI Launches Deep Research Agentic Capability in ChatGPT
By
–
“Today we’re launching deep research in ChatGPT, a new agentic capability that conducts multi-step research on the internet for complex tasks. It accomplishes in tens of minutes what would take a human many hours.” https://
openai.com/index/introduc
ing-deep-research/
… -
AI System Reliability: Low Hallucinations and Source Citation
By
–
it usually cites its sources and hallucinations seem pretty low
-
OpenAI Launches Deep Research Autonomous Assistant Tool
By
–
OpenAI just launched an autonomous research assistant, Deep Research. We've been testing it for a few days @Every and it's like a bazooka for the curious mind: – Give it a question, and it will autonomously search the web (or provided sources) to compile an answer
– It does -
Building a Real-Time Battleship Game Between Two LLMs
By
–
Earlier, also ~hour of vibe coding, I built a Battleship game wired up so that you see two LLMs (any two models you select) are fighting each other in real time. I don't have super strong stats yet on this but I believe 4o beats 4o-mini, lol.
-
Custom LLM Reader App for Interactive Book Analysis
By
–
Last ~hour I built a custom LLM reader app so while I read Wealth of Nations I can ask questions about any paragraph. When you click a paragraph and "Ask" it calls an LLM, builds context window of what this is, copy pastes the full chapter, the paragraph, and the question. Works
-
The Spectrum of LLM Assistance in Programming: From Traditional to Vibe Coding
By
–
The amount of LLM assist you receive is clearly some kind of a slider. All the way on the left you have programming as it existed ~3 years ago. All the way on the right you have vibe coding. Even vibe coding hasn't reached its final form yet. I'm still doing way too much.
-
Vibe Coding: Embracing AI-Powered Development Without Traditional Constraints
By
–
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper
-
Gemini’s search feature with citations
By
–
A similar feature exists on Gemini. It performs a search over a big amount of different resources (50-200, etc) and generates an output as a canvas with citations. Takes more than 2 mins typically
-
O1 as Reward Model for Output Selection
By
–
The code here yes, but concept is likely. It is quite likely they used o1 as a reward model/critic to choose from a group of outputs