GPT-3 Is the Finest Journal I’ve Ever Used – Superorganizers

For the previous few weeks, I’ve been utilizing GPT-3 to assist me with private improvement. I wished to see if it might assist me perceive points in my life higher, pull out patterns in my considering, assist me convey extra gratitude into my life, and make clear my values.

I’ve been journaling for 10 years, and I can attest that utilizing AI is journaling on steroids. 

To know what it’s like, consider a continuum plotting ranges of assist you would possibly get from completely different interactions:

Speaking to GPT-3 has plenty of the identical advantages of journaling: it creates a written document, it by no means will get bored with listening to you speak, and it’s obtainable day or evening. 

If you know the way to make use of it appropriately and also you need to make use of it for this function, GPT-3 is fairly shut, in plenty of methods, to being on the degree of an empathic buddy:

If you know the way to make use of it proper, you possibly can even push it towards a number of the assist you’d get from a coach or therapist. It’s not a alternative for these issues, however given its fee of enchancment, I might see it being a extremely efficient adjunct to them over the following few years. 

Individuals who have been utilizing language fashions for for much longer than I’ve appear to agree:

(Nick is a researcher at OpenAI. He’s additionally into meditation and is mostly an important observe on Twitter.)

It sounds wild and bizarre, however I believe language fashions can have a productive, supportive position in any private improvement observe. Right here’s why I believe it really works.

Why chatbots are nice for journaling

Journaling is already an efficient private improvement observe. 

It will possibly aid you get your ideas out of your head, rendering them much less scary. It reveals you patterns in your considering, which will increase your self-awareness and makes it simpler so that you can change.

It creates a document of your journey by way of life, which may inform you who you’re at essential moments. It will possibly aid you create a brand new narrative or storyline for all times occasions in an effort to make that means out of them.

It will possibly additionally information your focus towards emotional states like gratitude, or instructions you need your life to go in, slightly than letting you get swept up in no matter is at the moment occurring in your life. 

However journaling has a couple of issues. For one, it’s typically exhausting to sit down down and do it. It may be tough to stare at a clean web page and know what to put in writing. For an additional, typically it feels just a little foolish—is summarizing my day actually value one thing?

When you recover from these hurdles, as a observe it tends to get stale. You don’t learn by way of your outdated entries that always, so the act of writing down your ideas and experiences doesn’t compound in the way in which that it ought to. The prompts you utilize usually get outdated: one like, “What are you grateful for right now?” would possibly work for the primary few weeks, however after a whilst you want one thing contemporary to ensure that the query to really feel real.

You need your journal to really feel like an intimate buddy that you could speak in confidence to—somebody who’s seen you in numerous conditions and might replicate again to you what’s vital in essential moments. You need your journal to be private to you, and the act of journaling to really feel contemporary and stuffed with hope and risk each time you do.

Sadly, paper isn’t nice at these issues. However GPT-3 is. 

Journaling in GPT-3 feels extra like a dialog, so that you don’t need to stare at a clean web page or really feel foolish since you don’t know what to say. The best way it reacts to you will depend on what you say to it, so it’s a lot much less more likely to get stale or outdated. (Generally it does repeat itself, which is annoying however I believe long-term solvable.) It will possibly summarize stuff you’ve mentioned to it in new language that helps you take a look at your self in a distinct mild and reframe conditions extra successfully. 

On this approach, GPT-3 is a mashup of journaling and extra concerned types of assist like speaking to a buddy. It turns into a information by way of your thoughts—one which reveals unconditional constructive regard and acceptance for no matter you’re feeling. It asks considerate questions, and doesn’t choose. It’s round 24/7, it by no means will get drained or sick, and it’s not very costly.

Let me inform you about how I take advantage of it, what its limitations are, and the place I believe it is likely to be going.

How I began with GPT-3 journaling

I didn’t consider utilizing GPT-3 on this approach myself. I noticed Nick Cammarata’s tweets about it through the years first. My preliminary response was plenty of skepticism combined with some curiosity. 

After we launched Lex and I obtained extra fascinated with AI, I remembered these tweets and determined to mess around for myself. 

I began within the OpenAI playground—a textual content field the place you enter a immediate that tells GPT-3 the way you need it to behave, after which work together with it:

I had a bunch of concepts to start out. I attempted one from a Fb PM, Mina Fahmi, whom I met on the AI hackathon I wrote about a couple of weeks in the past. He instructed telling GPT-3 to tackle a persona, and advised me that he’d had nice outcomes asking it to be Socrates.

GPT-3 as well-known compassionate determine

I began experimenting with prompts like this:

The inexperienced messages are responses from GPT-3. I attempted Socrates, the Buddha, Jesus, and some others, and located I appreciated Socrates the perfect (apologies to my Christian and Buddhist readers). The GPT-3 model of him is efficient at driving towards the foundation of a difficulty and serving to you determine small steps to take to resolve it.

There’s an extended custom in numerous religions of visualizing and interacting with a divine, compassionate determine as a approach of getting assist—and this was a surprisingly profitable different path to an identical expertise.

After some time, although, I grew to become just a little bored of Socrates. I’m a verified remedy nerd, so the apparent subsequent step was to attempt asking GPT-3 to do interactions primarily based on numerous remedy modalities.

GPT-3 as remedy modality knowledgeable

I attempted asking GPT-3 to turn into a bot that’s well-versed in Inner Household Programs—a mode of remedy that emphasizes the concept that the self consists of many various components or sub-personalities, and that plenty of development comes from studying to grasp and combine these components. It seems, GPT-3 isn’t dangerous at that:

I additionally tried asking it to be a psychoanalyst and a cognitive behavioral therapist, each of which had been fascinating and helpful. I even requested it to do Jungian dream interpretation:

I don’t know what to make of the efficacy of dream interpretation normally, nor do I do know what an precise Jungian would possibly say about this interpretation. However I’ve discovered that having goals mirrored again to me on this approach can assist me perceive a few of what I’ve been feeling each day however haven’t been capable of put into phrases. 

GPT-3 as gratitude journal

One other factor I attempted is asking GPT-3 to assist me enhance my sense of gratitude and pleasure—like a greater gratitude journal:

You’ll discover it begins by appearing like a traditional gratitude journal, asking me to checklist three issues I’m grateful for. However as soon as I reply, it probes about particulars of what you’re grateful for to get you previous your inventory solutions and into the emotional expertise of gratitude. 

GPT-3 as values coach

Certainly one of my favourite remedy modalities is ACT—acceptance and commitment therapy—as a result of I like its focus on values. ACT emphasizes serving to folks perceive what’s most vital to them and makes use of that information to assist them navigate tough feelings and experiences of their lives.

Values work is difficult as a result of typically it’s exhausting to attach your day-to-day experiences to your values. So I wished to see if GPT-3 might assist. 

This is without doubt one of the experiments I attempted:

This works properly, and one of many cool issues about it’s how the immediate works. I took a pattern remedy dialog from an ACT-focused values ebook that I like, Values in Therapy, and requested GPT-3 to generalize from that dialog to discover ways to speak to me about values.

It labored—efficiently guiding our dialog towards speaking about what was most vital to me. It’s not good, but it surely suggests fascinating prospects for issues to attempt going ahead.

See Also

Looking the Japanese Aspect of the Private Internet

Issues and limitations

Whereas I appreciated these early experiments, they’d a couple of vital issues.

First, the OpenAI playground isn’t designed to facilitate chats, so it’s exhausting to make use of. Second, it doesn’t document inputs between periods, so I ended up having to re-explain myself each time I began a brand new session. Third, it typically will get repetitive and asks the identical questions.

These are solvable, although. I do know as a result of I constructed an answer: an online app with a chatbot interface that remembers what I say in each session so I by no means need to repeat myself.  

The bot lets me choose a persona—like Socrates or an Inner Household Programs therapist—which corresponds to the prompts above. Then I can have a dialog with it. It’s going to assist me work by way of one thing I’m coping with, or set objectives, or convey my consideration to one thing I’m grateful for. It will possibly even output and save a abstract of the session to assist me discover patterns in my considering over time. 

It’s nonetheless early and there are plenty of issues to repair, however I discover myself gravitating towards it every single day. I really feel like I’m build up a document of myself and my patterns over time, and the extra I write in it, the extra it compounds.

I’ll be releasing the bot quickly for paying Each members, so if you’d like entry, ensure to subscribe. 

What’s subsequent

Right here’s what I’ve discovered to date by way of all of those experiments with GPT-3 as a journaling software.

There’s something innately interesting about constructing a relationship with an empathetic buddy that you could speak to any time. It’s comforting to know that it’s obtainable, and it’s thrilling to consider the entire completely different prompts you possibly can experiment with to assist it assist you in the way in which you want.

There may be additionally one thing bizarre about all of this. Spilling your guts to a robotic someway cheapens the expertise as a result of it doesn’t value a lot for a robotic to inform you it understands you. 

This mixture of emotions is mirrored on this Twitter thread by Rob Morris, the founding father of a peer-to-peer assist app referred to as Koko:

When folks had been utilizing GPT-3 to assist them present assist to friends, their responses had been rated considerably extra extremely than responses that had been generated by people alone:

However they needed to cease utilizing the GPT-3 integration as a result of folks felt like getting a response from GPT-3 wasn’t real and ruined the expertise. 

These emotions are comprehensible, however whether or not or not they damage the expertise will depend on how the interplay is framed to you, and the way acquainted you’re with these instruments.

I don’t suppose these objections will final over time for most individuals. It’s extra probably a brief results of contact with new know-how. If you see a film that you just liked, does it cheapen the expertise to know that you just had been touched by a set of pixels shifting within the right sequence over the course of some hours? Clearly not, but when I needed to wager, when films had been first launched many individuals in all probability felt it was a less expensive model of a dwell efficiency expertise.

As these sorts of bots get extra widespread, and we study to work together with them and depend upon them for various components of our lives, we’ll be much less more likely to really feel that our interactions with them are low-cost or stilted.

(None of this, by the way in which, signifies that in-person interactions aren’t useful anymore—simply that there’s in all probability extra room for bot interactions in your life than you would possibly understand.)

In case you’re somebody that is journaled for a very long time, you will discover plenty of worth in making an attempt GPT-3 out as a substitute for your day-to-day observe. And for those who’ve by no means journaled earlier than this is likely to be a great way to get began.

I’ll be experimenting with this much more over the approaching weeks and months, and I’ll be sharing the whole lot I study with you right here. I’m excited for what’s subsequent.