14 chunks · 13 episodes
...le to the chat app that created them. Wouldn't it be cool if people could cache Deep Research reports publicly for others to draw from? There's a bunch of great papers in the literature that took decades and decades to be noticed and operation...
Imagine if your notebook did deep research on the things you care about while you slept.[gg]
...cs like War. A few dynamics of the game popped out to me, that I confirmed with Deep Research. Assuming no-op ties, in a game of War, whoever holds the high card can never lose it, so they never lose. If each card is unique, that means there's...
I kick off dozens of deep research style reports every day. Just random little hypotheses that occur to me that I want to dig into. Like having reasonably-well-researched content SEO i...
...: A Zero-Click, Service-Side Attack Exfiltrating Sensitive Data Using ChatGPT's Deep Research Agent.. Ars Technica's summary Eito Miyamura: "We got ChatGPT to leak your private email data… …All you need? The victim's email address" Note, this ...
... ends. If you want to dig in more, I fed my recent Bits and Bobs into ChatGPT's Deep Research and it gave a more in depth report diving into the parallels.
... in the era of AI. Imagine a private, turing-complete, coactive Notion. Imagine deep research that keeps running as new data comes in and amends itself.[lr]
Imagine Deep Research, but on your own private context. A tool that helps you tackle problems that are meaningful to you.
...on oriented, to be trusted to do things fully on your behalf. In my experience, Deep Research often gets tricked by SEO slop. The slopification of the internet means that most of the data is untrustworthy. A human looking at the SEO'd slop wou...
Imagine: Deep Research, but the output is a perfectly bespoke app that solves your precise need in this moment.
...inevitable that I was surprised by their surprise. I asked ChatGPT to prepare a Deep Research report on why it is and thought it did a pretty good job. The non-rivalrous nature of software and power of abstraction seem very relevant.
LLMs (including Deep Research) assume your question is coherent or a good one.[vc] It's very easy to accidentally trick yourself with some superficially good output on a fundament...
...spelling mistakes, write in all lower case, and generally sound unprofessional. Deep Research communicates in deeply cited multiple page reports. The first impression that gives is extraordinary but it often fails to be impressive the closer y...
...rect or smudged. It can help get you oriented in novel domains. If you think of Deep Research's output as a smudged map, it can still be useful, especially for domains that you're a novice in. Just don't take it too literally.