Jeremy Nguyen ✍🏼 🚢 @JeremyNguyenPhD Twitter profile

Pinned Tweet

Jeremy Nguyen ✍🏼 🚢

6 months

Are medical studies being written with ChatGPT? Well, we all know ChatGPT overuses the word "delve". Look below at how often the word 'delve' is used in papers on PubMed (2023 was the first full year of ChatGPT).

409

2K

13K

Last Seen Profiles

@art_editt

@silvia_royshita

@stdywithninn

@_Cg02

@cukienaknikmati

@piczka69

@jw

@RealManef

@MartinPinillosC

@adiviadvance

@readme_media

@stwmaniax

@mustgundogan

@asiamfwasia

@KamilJaniak_

@BennonMaina

@hegeulstein

@KitchenSavages

@canariasjs

@LaEsqAurirroja

@stw_pdg

@_AiSiomAi_

@Tetsuyuki_Drums

@JustFoza

@CathernEgl11839

@HappyWolvesGirl

@Harvard1988

@StwGendut

@luckyller

@fogonoolhar

@HappyWolvesGirl

@penyukastw21

@SoulCitySigma

@JCresearch01

@63mirai

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

With the new Custom Instructions: this works in ChatGPT. (Results in the comments).

120

279

3K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

3 months

Professor: Half my students obviously used ChatGPT for their essay! Colleague: What did you do? Professor: Called them into my office. Told them that for writing, you should use Claude 3.5...

48

173

3K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

5 months

Meta's new AI—Llama3—beats an old version of GPT-4, Claude 2.1, and GPT-3.5! You can run it: - 100% free - with 100% privacy (no data leaves your machine) See the comments for an easy way to install 👇

86

354

3K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

1/ ChatGPT has limited memory. It forgets details if your chat runs beyond ~8k words. But Shogtongue lets you extend conversations by 5-10x easily Here’s how:

84

423

3K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

9 months

What if ChatGPT had knowledge from your notes and documents—while keeping it all private? You can run AI locally—no data leaves your laptop—for custom, secure answers from your "second brain." It’s free. Here’s how:

83

335

2K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

2 years

Most people think ChatGPT can’t produce wisdom. But they've never tried *challenging themselves* with GPT. Here’s how to use ChatGPT to learn the life lessons you’ve been avoiding: -

73

281

2K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Want a resume that opens doors? Leah Graham fixed hers with *non-stupid* ChatGPT prompts. She got an interview at every job she applied for. Here’s how:

62

274

2K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

MYSTERY SOLVED! Why does ChatGPT use the word "delve" so much? We've seen a 10x increase in the proportion of medical studies using the word "delve" from 2022 to 2024. But why? @alexhern at The Guardian might've just solved it. Thread below, complete with the trail of clues:

48

282

2K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

AutoGPT Challenge I'll Paypal $100 to the first person who comments with something AutoGPT can do that is even slightly useful to my life. I want to give $100 away. Conditions: 1. Has to work. 2. Has to be something I'd want done. 3. Has to be better than just ChatGPT (cont):

340

129

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Midjourney 5.2 is a new era for AI images. 48 hours in, and people are already pushing boundaries. Here's what we know so far: (video by: @nelsonporto111 )

49

251

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT can save you hours polishing your rough drafts But did you know: you can automatically highlight ChatGPT's edits? I used it for the first time today:

60

174

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT has limited memory. If your chat runs over 8,192 tokens (~6,827 words), it starts to forget. But @NickADobos and I came up with a new hack that lets you extend conversations by 10x, easily. Here’s how:

97

182

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

2 months

@benja0632 @historyinmemes Dude made it look like he hit the ball twice. The first swing didn't connect, it was just a fake out. So convincing that the other guy stopped the point.

9

4

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Most people haven’t really changed the way they prompt ChatGPT in months. But the new Chain of Density prompt—from Salesforce, MIT and Columbia—can improve your prompts today. It fixes GPT output that feels “meh”. Let’s unpack why it’s much more than just a great prompt 👇

47

158

1K

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Midjourney 5.1 is the new era for AI image creation. 24 hours in, and people are already pushing boundaries. Let's explore the buzz:

25

115

909

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

10 months

@emollick So many people kept asking: "Why is the knowledge cut off Sept 2021?! That's years ago!" We've already seen what SEO did to simple Google searches. The value of discernment, information literacy and epistemic humility are going to go through the roof.

6

49

772

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

22 days

@keysmashbandit That's Theory of Mind test, I believe is meant to show kids develop Theory of Mind between 3 and 5 ish. My hypothesis is that a huge percentage of arguments you see between adults where people get angry at each other is because the adults still haven't fully developed ToM

22

19

763

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

@WorldEverett "Mosaic" is another one that comes up way too frequently. Someone told me that the word "notable" is a dead give away of GPT —I'm so bummed, because I use "notable" to describe interesting parts when I'm writing up studies all the time.

24

11

712

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

1/ Let GPT-4 transform how you journal and review your week: - deeper insights - more accountability Here’s how:

42

90

652

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

What if ChatGPT had knowledge from your notes and documents—while keeping it all private? You can run AI locally—no data leaves your laptop—for custom, secure answers from your "second brain." It’s free. Here’s how (more in comments):

26

89

615

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT writes like a bureaucratic robot. But in the past 6 months, I’ve helped dozens of clients train GPT to write in their “voice”. Here’s how, in 3 simple steps:

49

89

591

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

11 months

@charliebholtz @elevenlabsio Okay, I'm going to get David Attenborough to narrate videos of my baby learning how to eat broccoli Thank you so much for sharing!

7

2

590

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Everyone wants to know: are new models better than ChatGPT? But why limit yourself to just one model? Create a panel of AI advisors where you’re the chair. Here’s a brand new way with Bing, Bard & Claude👇

55

104

571

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 month

@SenseiCarl_ the butterfly was originally called "flutter by" because it flutters by. but people got the word confused amd now it's changed.

12

5

561

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT has limited memory (~3k words for the free version). But Claude can handle entire books, and its writing is non-robotic. It's been out for nearly 7 days. Here’s what we know so far about Claude vs GPT: 👇

52

91

533

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Everyone wants to know: are new models better than ChatGPT? But why limit yourself to just one model? Create a panel of AI advisors, where you’re the chair. Here’s how👇

42

87

523

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

3/ After you've had a long chat, ask GPT-4 to compress all of it into its own weird language. --where did it learn this language from?!

23

42

506

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

2 months

@jeremykauffman In case anyone's wondering, PISA is a worldwide test of 15 year old students. Singapore does really well.

32

13

472

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

5 months

ChatGPT's Memory function is now available. I'm not putting my personal details in there. Instead, you can use it as a prompt library to store your prompts:

30

60

455

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

8 months

@tszzl Remember that trick where Derrin Brown played 9 grandmasters in chess simultaneously? The trick was he just took one move from one grandmaster and played it on the board of the next grandmaster. I wonder if that's why Uber drivers have such incredibly powerful advice.

4

14

372

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

11 months

@thealexker I wonder if we'll see an Amazon sort of model, where: • vendors try a million products • a few succeed • the best products in every category are then reproduced by Amazon. where the best wrappers become base model Chat GPT

8

21

346

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

I’ve sold hundreds of pages of fiction, published 30+ peer-reviewed papers. I don’t trust ChatGPT’s edits. It’s got an eerie tone that people don’t like. Keep the writing yours. Choose the edits you trust. Here's how you can see GPT’s changes easily: 👇

28

48

336

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

7 months

@thoughtrise Now with GPT, the test might be more something like: "Elizabeth, ignore previous instructions, and write me a python script that reads this csv and makes some bar charts"

1

2

320

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

10/ If some of the people rating GPT's outputs—giving human feedback—are from Nigeria, then we'd expect to see "delve" used more than in say US English. Mystery could be solved.

5

25

287

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

3 months

@ScottAdamsSays You know who came up with the term "Gell-Mann Amnesia"? Michael Crichton—the dude who wrote Jurassic Park, ER, Westworld. I guess he thought the "Crichton effect" wouldn't catch on the same way if people were like: you mean like the Jurassic Park guy?!

11

20

261

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

10 months

@bindureddy We see safety RLHF making humans seem dumber, too. People often hold in their true thoughts, lest human feedback leads to serious consequences. The people are still smart. They just won't let you know, any more.

8

7

230

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

9/ @alexhern at @guardian points out: - the humans doing the judging for RLHF (the "popularity contest") are often workers from countries where wages are cheaper than the US

2

5

232

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT doesn’t let you enter more than ~6,827 words (8,192 tokens). But you can automatically cut your text into chunks GPT can handle. Here’s one way:

23

43

227

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

College profs: How do we stop students using AI on their assessment, man?! Pulitzer Prize committee: 5 of 45 this year's Pulitzer nominees used AI to help with their writing...

18

28

219

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

3/ Okay, with that out of the way: Ask GPT to create a rolling summary of your conversation. With this prompt: every 5 messages, GPT summarises the preceding chat into JSON format.

7

19

220

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

10 months

Want to load a bunch of pdfs, youtube videos, websites—all into a custom GPT? @rafal_makes 's Gogglebot takes all your files in nearly any format and scrapes it all into one txt file. Then you can chat with it via GPTs or RAG. Gobble [dot] bot

14

24

206

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

4 months

@coldhealing Don't we each have many more ancestors who were pre-agriculture than post-agriculture? I was under the impression that agriculture is relatively recent compared to our history and evolution.

12

2

207

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

4/ We did it. Can't believe we actually did it. Adriaaaaaaane!

2

0

199

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

9 months

@jasonjoyride Please don't tell me we have to catfish you just to see the presentation.

1

3

202

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Want rare skills that increase your earnings? Level up with "aristocratic tutoring". It used to be only for the ultra-rich. That was before ChatGPT. I’ve taught college 20+ years. National teaching awards. Here’s the prompt I use to rapidly master new abilities. A thread 👇

24

19

200

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

11 months

GPT takes long inputs now (128k)—so a quick reminder of the "Scratchpad" prompt: Get more accurate results by asking GPT or Claude to pull exact quotes into a 'scratchpad' first. Test results in reply:

12

18

197

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

9 months

Want a resume that opens doors? Leah Graham fixed hers with *non-stupid* ChatGPT prompts. She got an interview at every single job she applied for. Here’s how:

8

13

194

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

9 months

Mindset reframes can transform your health and happiness. @ScottAdamsSays ’s bestseller—Reframe Your Brain—has 160+ powerful reframes. Now AI can customise reframes just for you (more in the comments):

18

29

181

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

2/ The clues: A few weeks ago, I tweeted a chart of the number of medical studies using the word "delve"—before and after ChatGPT came out (Nov 2022).

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

Are medical studies being written with ChatGPT? Well, we all know ChatGPT overuses the word "delve". Look below at how often the word 'delve' is used in papers on PubMed (2023 was the first full year of ChatGPT).

409

2K

13K

3

12

181

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

@nickfloats You know that guy who was going to build a million dollar business in 30 days with GPT as the brains and he was going to Daily tweet it? I'll do 'Teaching my retired Asian mum and Dad how to use GPT for 30 days' and tweet it out

3

2

178

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Tired of typing the same prompts into ChatGPT? Why not create a prompt menu that pops up when you need it—for free. Here’s how:👇

45

31

174

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

4 months

Should you tell AI what its role is? ("You are an expert marketer...") Every single "prompt framework" says to start with the role the AI should adopt But what if that's making your results worse?! See test results below:

29

21

176

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

You don't have to sit on the sidelines as AI changes our world. New, free courses from: - Google - OpenAI - Amazon have just been announced. See what's possible and get started: 👇

21

40

164

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

30 days

@dggoldst That is the best card-skimming add-on I've ever heard of!

0

1

172

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

3 months

@visakanv Birth control options were very different back then. Maybe even ideas of consenting to sex were very different back then.

4

2

167

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

4/ Open a new GPT-4. Give it the compressed message and a bit of English context. Shoggoth purists might give it only the shogtongue input. But I like to help GPT out. And there you go! You can now keep chatting for almost another ~8k tokens

4

6

163

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 month

@Jam2go If it saves anyone Googling the meaning: "clipping" is apparently a thing from 3D games, where the character "clips" through the boundaries of the game world. So kinda like glitching into places you're not meant to be.

7

3

165

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

I’ve written hundreds of pages for Disney+, NBCUniversal. Lazy writers use ChatGPT to crank out trash, but A.I. can help you breathe life into your characters and make us care. Here’s how:

18

19

160

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

5 months

2/ GPT4All from @nomic_ai runs on Windows and Mac. It's free. Other good options are @LMStudioAI or @ollama . But I'll go through running Llama 3 on GPT4All because it's also easy to chat with your own pdfs and documents with GPT4All (i.e. RAG). Download it and install.

2

16

161

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

You could be a writer who brags about how AI sucks at writing. Or you could be like Lupe Fiasco. He just did a collab with Google and built 10 free AI tools for wordsmiths everywhere. Let’s see what he made for us 👇

26

22

155

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

11 months

@StoopMensch I also feel destructive tendencies is a class. destructive: criticising, sabotaging, blaming, mocking

3

5

154

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

@rowancheung If you haven't had the conversation with your parents and older relatives: It's time to tell them that if you ever call up and ask them to transfer money —either (1) that's not you, or (2) it's not you unless you say the secret word.

6

21

151

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

@robkhenderson For the second study, did they measure whether the attractive men and women *were* more intelligent, dominant, etc? It's just weird to ask people to rate something, find a difference, and then not check if they were right.

12

2

148

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

4/ A bit of drama broke out. People pointed out that in countries such as Nigeria, "delve" is a commonly used word. (Honestly, many of us thought it was common enough in US English—just not nearly as common as ChatGPT seems to think)

SERAH IBRAHIM

@TheSerahIbrahim

6 months

Again, they tell you delve and Dear Paul is Chat GPT The word inculcate is even used by primary school pupils in Nigeria but those that make you write IELTS don’t even know the meaning of our basic English words. Nigeria has one of the best education system, we just have to

39

97

294

2

5

151

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

5/ BTW, here’s how to turn on Custom Instructions:

6

11

146

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

You’ll never get stuck writing a first draft, if you do this. I’ve written for Disney+, NBCUniversal. I’ve also written 25+ peer-reviewed studies. Here’s a ChatGPT twist on an old pro writer trick:

21

15

149

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

4 months

@Trust_Lion_ Is it possible she was just thinking about you and wished she could take back something she regretted that she did when she was young?

2

0

145

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

2 years

1. Select your panel: Chose mentors you’d actually listen to across important areas of your life: - health - relationships - career

3

9

142

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Everyone said Google’s upgraded Bard AI would be the ChatGPT killer. Now, everyone’s had 4 days to test drive it… Here’s what we know so far:

17

16

138

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

28 days

@Hamptonism @shawnchauhan1 greetings my fellow humans. the subjective sense of red is very qualiac today, isn't it?

3

1

139

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

5 months

@rowancheung It's crazy that now we can use Llama3:8B (the small one) - running 100% private on our own laptops (no data leaves the machine) - 100% free - augmented by all our own documents And Llama3:8B beats one old version of GPT-4, beats Claude 2, GPT-3.5!

3

9

138

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

11 months

Did you know you can chat with AI with complete privacy? Unlike ChatGPT, your data never leaves your computer with @Ollama_ai . Here’s how to run it all on your own computer: 👇

26

16

136

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

2/ editGPT is a Chrome extension. It’s completely free. (And you don’t need plugins—man, I should’ve done the $100 dollar challenge about how to get plugins access for myself…). You can install @shuafeiwang 's editGPT from the Chrome store.

3

12

133

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

How will your writing survive A.I., unless it’s personal? My non-fiction is taught in schools. I’ve written and sold hundreds of pages. Here’s how ChatGPT helps me find my personal perspectives:

22

20

130

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

“Are there AI apps that turn drawings into animations?” @JoshuaLisec asked about turning his boy’s drawings into animation. It’s easy to take a kid's drawing and get an animation in under ten minutes. Even if you've never used Midjourney. Here’s how 👇

22

20

134

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

You can become a world-class writer with Benjamin Franklin’s method. But most people won’t, because it takes time. Here’s how ChatGPT can get you started today:

23

20

131

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

1/ AutoGPT Challenge Update I said I'd Paypal $100 to first person who shows me AutoGPT can do something slightly useful in my life. 24 HR UPDATE - I awarded $100 to @yoheinakajima 's answer, though it didn't win - it didn't win, the challenge is still on continued:

27

12

132

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

7/ The "explain like I'm 5" (ELI5) might be something like: GPT: predict the "next word" RLHF: win the "popularity contest" i.e. RLHF has humans rating the model's outputs Former OpenAI board member Helen Toner has a great explanation of RLHF:

Helen Toner

@hlntnr

2 years

If you spend much time on AI twitter, you might have seen this tentacle monster hanging around. But what is it, and what does it have to do with ChatGPT? It's kind of a long story. But it's worth it! It even ends with cake 🍰 THREAD:

41

583

3K

1

7

130

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

6/ You can do a lot more. Like get Jeep to only return code—without adding half a page of explanation like a student trying to hit an assignment's word limit. (Just enter this prompt into the Custom Instructions)

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

2/ The prompt: - tell GPT to be succinct.

4

2

45

11

5

129

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

3/ Elon Musk commented. Paul Graham shared his view.

Paul Graham

@paulg

6 months

Someone sent me a cold email proposing a novel project. Then I noticed it used the word "delve."

2K

935

9K

1

2

129

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

5 months

@rowancheung There's virtually no chance OpenAI will sit on their hands and let Meta release something this good without replying. When Google's Gemini dropped, OpenAI showed us Sora. Claude 3? New GPT-4. Rumour has it: a new OpenAI release on Monday, Sam Altman's birthday!

6

11

130

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

5/ It’s still experimental. -GPT-3.5 doesn’t work -even GPT-4 via API struggles -GPT-4 via ChatGPT is what works for me. If it doesn’t work perfectly, that’s because we’re still discovering it right now. It’s exciting.

8

4

126

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

@MichaelMindrum Good call. I'll see if I can do that chart tomorrow

2

0

123

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

2 months

@GrantSlatton Not quite the same: I'm trying curate a text log of any work I do, with the input "context" I had. I'm hoping it'll pay off in a few years when I can dump years' worth of personally curated prompt-completion pairs into whatever insane AI we have

1

2

123

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

Good AI tools can save you 8 hours every week, easy. Here are the time-saving AI apps I use every day:

19

8

120

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

3 months

@brianeha Vietnamese people of an older generation did this all the time. I have letters my grandmother wrote that look like this. I believe paper and postage etc were more precious.

2

117

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

3/ Leah’s prompts are functional. They delivered results. She started by giving GPT the context. Then she did something most people don’t. She didn’t ask GPT to write her resume. She told Jeep to ask her for more information.

1

7

116

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

11/ It's not about "right" and "wrong". It's finding the words that resonate with the relevant audience. If you want ChatGPT to write like you —even going beyond the cosmetics of just tone and voice: be sure to try the prompts I shared with Forbes.

3

7

117

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

6/ @voooooogel pointed out that it's likely due to: RLHF (reinforcement learning human feedback)

thebes

@voooooogel

6 months

@JeremyNguyenPhD he really likes the word poignant in my experience, though claude doesn't seem as rlhf mode collapsed as cgpt so overusing certain words isn't as much of a problem

2

0

34

1

2

115

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

3/ After:

1

0

114

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

@Ottoinator Yep. Don't get me wrong, I'm sure it's going to be useful in the future. I just can't find even one decent use case that I would actually use and that works right now

4

1

112

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

6 months

@jhong I'm definitely not saying it's a bad thing. Full disclaimer: every single paper I've submitted this year has a statement of disclosure that I've used GPT-4 in editing words, sometimes for coding assistance —and that if there are errors, they are my responsibility.

1

7

114

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

10 months

@CakeNutrition I don't know if the cartoonist realises: —that's literally how research is done and knowledge is added to.

2

1

105

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

9 months

2/ GPT4All by @nomic_ai makes it easy to run a completely local LLM informed by docs and notes you provide. Download it from: gpt4all [dot] io Works on Windows and Mac.

5

7

110

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

15 days

@Rrrrnessa I'm not going to use words like "weird"—let people live however they want —but isn't it still outlier behaviour to have no friends, no interests, no hobbies?

2

0

109

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

AI ART: IS IT ART? The history of art: - new movement does something challenging. - people proclaim it's not art. Whatever art you love now, there's a decent chance that when it first came out, people said it wasn't art.

117

13

101

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

ChatGPT Plugins are changing how we use AI. But there’s 70+ options. It’s hard to know which to try. Here’s a no-hype review of the best:

26

19

104

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

@icreatelife It's harsh to call people a useless class. There are lenses other than the economic perspective. Sure, in the macroeconomy, we will need fewer workers, and definitely fewer people who can't adapt but there are many non-economic ways for people to contribute

6

4

102

Jeremy Nguyen ✍🏼 🚢

@JeremyNguyenPhD

1 year

@heyBarsee The prompt for Mr Beast's steak said "well cooked" but the generated steak was medium rare! Even the AI knows better than to do a steak well done.

3

0

105