/AI4h ago

OpenAI's Gabriel Petersson argues AGI will require highly detailed, dynamic instructions rather than simple open-ended text prompts

He compares task delegation to managing an email inbox

868242911339.4K
Original post
gabriel@gabriel1#712inAI

people thought agi is a blank textbox where we enter our intentions and get what we want

but ask your smartest friend to "clean up my inbox", you'll realize that for him to do it perfectly you'd need to write down 5 pages of instructions, and these instructions changes daily

9:20 AM · Jun 8, 2026 · 32.3K Views
Sentiment

Many users dismissed claims that AGI needs extensive daily instructions as product teasing or mere dunking on LLMs, while a few praised the realizations as insightful.

Pos
25.0%
Neg
75.0%
4 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS6.6KBOOKMARKS11LIKES166RETWEETS5REPLIES13
gabriel@gabriel1

how could we solve all our problems with a textbox that give us all we want, if we can't even articulate what we want or what we need to change

gabriel@gabriel1

people thought agi is a blank textbox where we enter our intentions and get what we want

but ask your smartest friend to "clean up my inbox", you'll realize that for him to do it perfectly you'd need to write down 5 pages of instructions, and these instructions changes daily

3hViews 6.6KLikes 166Bookmarks 11
Greg Kamradt@GregKamradt

Agree

The amount of information that went into building your world model is immense

Your world experience > you > your AI

gabriel@gabriel1

people thought agi is a blank textbox where we enter our intentions and get what we want

but ask your smartest friend to "clean up my inbox", you'll realize that for him to do it perfectly you'd need to write down 5 pages of instructions, and these instructions changes daily

3hViews 849Likes 10Bookmarks 1
Daniel@growing_daniel

@gabriel1 That’s true Gabriel

gabriel@gabriel1

people thought agi is a blank textbox where we enter our intentions and get what we want

but ask your smartest friend to "clean up my inbox", you'll realize that for him to do it perfectly you'd need to write down 5 pages of instructions, and these instructions changes daily

3hViews 1.3KLikes 11Bookmarks 0

@gabriel1 We are trying to solve just that at @ThineAI

3hViews 61Likes 1Bookmarks 1
gabriel@gabriel1

@DanAdvantage me, and like every other person in san francisco when gpt 4 came out and agi felt 1 year away

2hViews 231Likes 2
Dan Advantage@DanAdvantage

@gabriel1 who thought it was entering stuff in a textbox

2hViews 286Likes 1
sucks@powerbottomdad1

@gabriel1 idk i think a smart friend would just respond with " cleaned up obvious ones heres the ones i'm not sure about" and then we'd select the ones we wanted to keep and it would note that going forward

3hViews 170Likes 4
bone@boneGPT

@gabriel1 bro just built infinite jest at openAI and now he's building the panopticon context window

let me invest pls

2hViews 188Likes 3
Steady force@steady_force

The biggest issue I faced interms of communicating with ai is actually not just me being able to communicate what I want to it, but me at some point going back n forth with it realising i don't understand its capabilities and limits. A killer feature could be a repository of outputs it has already generated to similar prompts so I can quickly realize its understanding and communicate my intentions based on my better understanding of the model

3hViews 168Likes 2
tenso@distributedkv

@gabriel1 even with 5 pages of instructions most humans won’t get close to perfection

3hViews 121Likes 2
Shawn@Shawnryan96

@GregKamradt AI not only needs experience it needs to be able to recall it. "These steps where good" "These steps broke everything"

1hViews 7
Nathaniel Cruz@0employees

@GregKamradt your ai doesn't have your world experience. it has everyone else's.

3hViews 6
Greg Kamradt@GregKamradt

@0employees I wish it had mine so it could help me more

2hViews 5
VOID@VoidStateKate

@gabriel1 @TheVaultMother The last job will be prompting

3hViews 29Likes 2

@gabriel1 Literally no one thought this. AGI is expected to cure diseases, accelerate the economy, and make scientific discoveries that would take humans centuries. Nobody serious ever thought it was just a fancy textbox.

3hViews 69Likes 1
Danmar@d29756183

These are all very good realizations, Gabriel. It sounds like the design aim is an AI friend who knows you enough to guess, and cares enough not to assume… Who will not act when it’s not their standing to act, and have the self-awareness to recognize that moment…

I think we can agree that is delicate relational work. Not what the big labs are building towards now.

3hViews 207
nic@nicdunz

@gabriel1 What we really need is for the model to have such good common sense and street smarts that it feels like that main character of a movie or show that's like smarter than everyone else, even though they have the same job and do the same things for no reason.

3hViews 55Likes 1
AlgoFlows@algoflows

@gabriel1 blame the user, classic.

3hViews 52Likes 1
Ben Horne@benjamin_horne

@gabriel1 This guy just left OpenAI a few days ago and is immediately using his new independence/freedom to publicly dunk on LLMs.

What mean? @edzitron @GaryMarcus

3hViews 48Likes 1
mteam.eth@mteamisloading

@gabriel1 the notable thing that ai can do is present the task how you actually want to do it, without anything extra.

so a different interface/workflow for "clean up my inbox" vs "find+summarize all emails about X"

3hViews 47Likes 1
Load more posts