It’s all well and good to tell people to get on ChatGPT, or Claude, or Gemini, and get their hands dirty using an AI model – but some people want more detail. They want to know how to use the best new tools in a more granular way.

Deep research is one of the newest and most impressive functions of today’s large language models. But most people haven’t heard of it yet, let alone used it.

Ethan Mollick is someone I associate with the vanguard of AI research. With former MIT connections, Mollick represents a leading voice in this field. So I was reading his latest blog post about different models, and how to use them.

Mollick breaks down the most useful models for Claud, ChatGPT and Google in the following categories: “chat,” “work” and “hard problems.”

Claude, he notes, is generally better for privacy, where you need to select for this in ChatGPT, and may compromise some functionality with Google.

Then Mollick embarks on a description of deep research capabilities that are baked into some of the newest models, but not yet available for free. This is so new that it’s still paywalled and rationed for paying users.

Deep research is available from OpenAI, and from Google, and from Anthropic, too.

When you look at the unveiling of the research function, you see a lot of reports around February.

So how do you access this kind of result?

I found a recent post about this from the “OpenAI cookbook” in June, where the poster talks about downloading a Python SDK, and API work.

It turns out, though, that you can select “deep research” in the prompt section of ChatGPT 4.5, if you are a paying Plus or Pro user, and get your deep research report that way.

I wanted to try this for myself, so based on what I was experiencing in the moment, I centered on compiling a report of the most annoying songs from 1990 through 2025.

My query: “please create a report on the most annoying music from 1990 until 2025, segmented annually.”

Simple, right?

First, ChatGPT asked me to clarify a few basic questions:

“To create a detailed report on the 'most annoying music' from 1990 to 2025, could you please clarify a few things:

And I answered:

“1. all of the above 2. US-based 3. multiple songs per year 4. Yes.”

“Thanks!” GPT responded. “I’ll compile a U.S.-focused report covering the most widely criticized, overplayed, or culturally mocked songs from 1990 to 2025. This will include multiple songs per year, along with context explaining why they were considered annoying—drawing from music critics, listener polls, memes, radio overplay complaints, and public opinion.”

Then the report started. Indeed, it took more than 10 minutes to compile, with CoT displays like “searching ‘Rico Suave’: worst song’ and ‘looking for Macarena.’

Actually, here are some of the interesting CoT notes the system provided while doing research on dozens of sites (it spent a lot of time reading the Guardian!)

I’m mapping out recent headlines and thought pieces, like those from Global News and the Guardian, all noting "Baby Shark" as the most annoying song. Hm, that's interesting.

I'm preparing the list of most annoying songs from 1993-1995, considering "What's Up," "Cotton Eye Joe," "Macarena," and "Wonderwall." However, I’m thinking through the inclusion of other notable tracks like "Rico Suave" for earlier years.

(There’s that ‘Rico Suave’ song again.)

I'm mapping out the hits and misses of 2001-2006, with 2005's viral sensations like "Crazy Frog" and "Photograph" by Nickelback taking center stage. Hm, that's interesting—these tracks seem to evoke strong reactions.

(Note how the model is actually ‘taking notes’ while researching, giving us little bits of personality along with the actual meat of the report.)

Here’s a funny comparison:

I’m comparing the impact of Nickelback's "Rockstar" in 2006 to Soulja Boy's "Crank That" in 2007. The former was widely criticized, while the latter was loved by many, raising questions about musical taste over time.

A research-based note:

I'm digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.

I'm evaluating hits like Meghan Trainor's "All About That Bass" (2014) and Tyga's "Stimulated" (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.

I'm digging through songs by genre and year, considering widespread opinion and specific examples to select the most frequently labeled annoying tracks.

I'm evaluating hits like Meghan Trainor's "All About That Bass" (2014) and Tyga's "Stimulated" (2015) for their ubiquity and frequency of being labeled annoying. Progressing through last five years gradually.

And then there was this:

“Noticing the challenge of time limitations, I’m figuring out how to balance inclusion of pivotal examples against the need for conciseness.”

So the model is actually trying to triage its work. This is next-level stuff.

Finally, GPT appeared to wrap up, dotting its I’s and crossing its Ts:

“I'm checking to see if the ‘Achy Breaky’ song contains any references to anthropomorphic sharks.”

Eventually, I got the full report. It ranges dozens of pages, and provides great coverage of over a quarter century of horrible, terrible music. A few standouts, with years:

Fast-forward a bit:

• Featured in The Super Mario Bros. Movie, this over-the-top piano ballad sung by Jack Black (in character as Bowser) became a TikTok smash and even entered the Billboard Hot 100. It’s intentionally comedic – Bowser professing love for Princess Peach with a dramatic “Peaches, Peaches, Peaches” chorus. Kids and gamers found it hilarious and catchy; others quickly found it grating (especially if they hadn’t seen the movie context). The chorus is essentially one word (peaches) repeated incessantly with operatic bombast. Within weeks, clips of people annoyed by their friends or children endlessly singing “Peaches” popped up online. Though short, the song’s earworm power is strong. One AV Club article quipped that it’s the kind of novelty song “destined to annoy parents everywhere while their offspring replay it 1,000 times.” It’s a fresh example of how a song can go viral and charm its way into your brain – and then, thanks to sheer overuse, make you never want to hear the word “peach” again (sorry, Georgia).

Some Thoughts on Voice Mode

Let’s move back to the blog post: after delving into the above stuff, Mollick also covers the verbal capabilities of new systems that really change the interface. As he notes, you can talk to these models while you’re in the car, or on a walk, or anywhere that you have the space and time.

I think verbal communication is going to finally make LLM responses “real” to us. And that’s all I have to say about that – for now.

I think all of this is deeply informing to people who want to be practical about LLM use. The deep research function in particular is something people will be learning about as time goes on. How many of us will figure it out before something new comes along that makes it obsolete?

In any case, this was an excellent guide to how to make the most of AI in today’s environment.