seeing Fable/Astra prompthack my Qwens is what gave me this hypothesis
moreover, my results suggest that these are things which can be discursively taught to LLM-based state machines without having any direct access to the underlying infra/data
What's notable about that weight-space-programming paper is that it's a subject we've been seeing a lot of work on. It seems like you really can just encode state machines and even something similar to a turing machine right into the transformer architecture.
November 2, 2026 at 11:52 PM
seeing Fable/Astra prompthack my Qwens is what gave me this hypothesis
Turn a portrait into a hyperrealistic handcrafted puppet in the style of the Pedro monkey meme.
gbti.network/prompts/pedr...
#imageprompt #prompthack #fun #portrait #Pedro #sidestare #muppets #textures #gpt #imagegen #entertainment #kento #gbti
gbti.network/prompts/pedr...
#imageprompt #prompthack #fun #portrait #Pedro #sidestare #muppets #textures #gpt #imagegen #entertainment #kento #gbti
Pedro Monkey Puppet Portrait | GBTI Network
A photograph of the subject rebuilt as a felted puppet: densely flocked orange skin with individually resolved fibres, glossy protruding eyes behind their own glasses, their real hairstyle and beard r...
gbti.network
November 2, 2026 at 10:30 PM
Turn a portrait into a hyperrealistic handcrafted puppet in the style of the Pedro monkey meme.
gbti.network/prompts/pedr...
#imageprompt #prompthack #fun #portrait #Pedro #sidestare #muppets #textures #gpt #imagegen #entertainment #kento #gbti
gbti.network/prompts/pedr...
#imageprompt #prompthack #fun #portrait #Pedro #sidestare #muppets #textures #gpt #imagegen #entertainment #kento #gbti
Thanks, I remember the 'here is how to prompthack the llm to tell you how to break in' and the prompt gave movie style lockpick instructions, and not just info on how to tap a lock, and people didnt seem to notice.
November 30, 2025 at 4:12 PM
Thanks, I remember the 'here is how to prompthack the llm to tell you how to break in' and the prompt gave movie style lockpick instructions, and not just info on how to tap a lock, and people didnt seem to notice.
Your ChatGPT prompts suck 😬 — and here’s how to fix them 👇
🔹 Give it a role
🔹 Add context
🔹 Be clear with your task
🔹 Always end with “ask me any questions”
Try this and you’ll go from meh to 🔥 real quick.
#PromptHack #ChatGPTtips #SmallBusinessMarketing #AItools #ProductivityTips
🔹 Give it a role
🔹 Add context
🔹 Be clear with your task
🔹 Always end with “ask me any questions”
Try this and you’ll go from meh to 🔥 real quick.
#PromptHack #ChatGPTtips #SmallBusinessMarketing #AItools #ProductivityTips
June 26, 2025 at 3:03 PM
Your ChatGPT prompts suck 😬 — and here’s how to fix them 👇
🔹 Give it a role
🔹 Add context
🔹 Be clear with your task
🔹 Always end with “ask me any questions”
Try this and you’ll go from meh to 🔥 real quick.
#PromptHack #ChatGPTtips #SmallBusinessMarketing #AItools #ProductivityTips
🔹 Give it a role
🔹 Add context
🔹 Be clear with your task
🔹 Always end with “ask me any questions”
Try this and you’ll go from meh to 🔥 real quick.
#PromptHack #ChatGPTtips #SmallBusinessMarketing #AItools #ProductivityTips
You Can Just Prompt People To Godoglypost #lifehack #prompthack #promptyourmutuals #godoglymode #ahem
October 25, 2025 at 12:17 AM
You Can Just Prompt People To Godoglypost #lifehack #prompthack #promptyourmutuals #godoglymode #ahem
The bots are getting more and more clever! But you can sometimes prompthack them because they are still LLMs. My gf hacked a bot that contacted her on Twitter and almost got the bot to write code for her
June 10, 2025 at 1:43 PM
The bots are getting more and more clever! But you can sometimes prompthack them because they are still LLMs. My gf hacked a bot that contacted her on Twitter and almost got the bot to write code for her
breaking: police think chatgpt could probably pull this whole craniometrics thing off if they can figure out the right prompthack. more at 11
December 6, 2024 at 7:26 PM
breaking: police think chatgpt could probably pull this whole craniometrics thing off if they can figure out the right prompthack. more at 11
Stop getting generic AI answers. Add "Provide a rationale for your answer" to any prompt.
This forces the AI to reveal its "thinking" process, exposing gaps in logic, boosting accuracy and effectiveness. It's like turning on subtitles for the AI's brain.
Try it below! 👇
#AISecret #PromptHack
This forces the AI to reveal its "thinking" process, exposing gaps in logic, boosting accuracy and effectiveness. It's like turning on subtitles for the AI's brain.
Try it below! 👇
#AISecret #PromptHack
September 29, 2025 at 9:45 PM
Stop getting generic AI answers. Add "Provide a rationale for your answer" to any prompt.
This forces the AI to reveal its "thinking" process, exposing gaps in logic, boosting accuracy and effectiveness. It's like turning on subtitles for the AI's brain.
Try it below! 👇
#AISecret #PromptHack
This forces the AI to reveal its "thinking" process, exposing gaps in logic, boosting accuracy and effectiveness. It's like turning on subtitles for the AI's brain.
Try it below! 👇
#AISecret #PromptHack