Olivia
Online
Haris Mekic
@G0DHM
***777***
Former Yugoslav Republic of Ma
Joined September 2009
320 Following
89 Followers
22 Posts
Pinned Tweet
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: https://t.co/bwn0sximKZ
@theo Theo, i do hope you read your comments i would like to share an architecture and engineering that i open sourced that i used Fable to publish it. Fable told me that is time to open source it and bring it up front for testing
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
Claude Managed Agents can operate in a sandbox you control, on your own infrastructure or with any provider you choose.
Today we added new guides for @blaxelAI, @e2b, @googlecloud, @namespacelabs, and @superserve_ai, so you can choose the best fit for your use case.
Who to follow
@asaio87 https://t.co/YfubZCkhag
I open sourced my architecture and engineering on how i have been using Claude, and it is published and finalized with Fable, if you have time take a look at it
It was my passion to become a programmer but had to take different path, working for UN and EU, but AI tought me and while watching AI work and keep asking it atleast i have an idea what you guys work, it might not make a programmer but i made a architecture and engineering with AI, i am sharing it with you, this is a open source, and AI published it because i am not a programmer 😀 would love to hear from you as programmer what i have
https://t.co/O1zgE0TYLD
https://t.co/8Xjv4uqnTG
You are far more dangerous to your startup than competitors are. A hundred times more startups die from poor execution by their founders than are killed by competitors.
@zeeg https://t.co/YfubZCkOZO
https://t.co/7lIHaTWjcb
@zeeg I open sourced my AI journey, it is my architecture and engineering of how i use AI models, i would love to be skinned and to know how bumpy is my journey, the article is published by Fable.
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@thdxr I am working on something and i need people to tell me what to work on, would appreciate your eyes and insights
https://t.co/r0Wt5TXMJc
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@Star_Knight12 https://t.co/r0Wt5TXMJc
Prasenjit, ask your AIs to read this, and tell me what you think, i open sourced my architecture and engineering, who knows maybe you can tell me where i stand, also i asked Fable to post everything because why not.
Thanks, will be waiting
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
Hey Taniya, you as python developer should know exactly where i stand, would love of you could spare a lil time and check my architecture and engineering that i am using for gliding trough AI models, heads up, i used Fable to post everything doors opened, and i opened sourced it.
Thanks
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@Amank1412 Hey, i opensourced my way of using AI models, maybe this will give you a weekend TO DO list, i would love to hear from you, your thoughts.
I used Fable, to blow it out.
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
pitch your startup
i'll pick 3 to feature in my newsletter sent to +2k people
Hi Victor, i am Haris been working for 15 years in major projects as PM - OM under UN and EU, I've always wanted to code but never had the balls to learn it, thanks to AI I've been able to test and work on something. That something that i want to pitch to you is my architecture and engineering of how i have been using AI models, today i decided to open source ot and used Fable to write a Article and post everything on github, maybe i have something maybe i don't, if you have time to look at it who knows maybe you will pick me.
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@billgnofficial Hey, i am sharing my journey into a 6 months working with AI, i open sourced it and let Fable write an article and post it on GITHUB. Would love to hear actual insights. Thanks
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@HelloVyom Sharing my journey and open source of my engineering and architecture, it is a new path for me, would love to hear your opinion, the article is written by Fable.
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
@automateitup @claudeai Thanks for the shared insight, whole point was for AI to write it, if you have time check my github and the research. Let me know what you think
https://t.co/a3Hrix0dOs
In January my first commit was an empty website scaffold. No team, no funding, one man and an AI, evenings turning into mornings.
People ask what "building with AI" actually looks like. For me it was never prompts. It was conversation. I watched how it worked, and when it drifted I told it the truth in one plain sentence and each sentence became a permanent part of the system:
"You are avoiding out of fear." that became its anti-avoidance discipline. It now runs a six-question test before it's allowed to defer anything.
"You keep asking me." that became the rule that it executes what I already approved instead of asking again.
"You say not stopping but you stopped." that became the discipline that momentum can't be performed, only practiced.
"No seals, no bullshit let it see everything." that became the full-data edition of the assessment, every real number measured live and published.
"You are holding back." I said that this week. Within the hour my GitHub profile was rewritten and a launch plan was in my hands.
Around 280 of those moments are logged. Not one model weight was touched. That is the whole method: honesty, repeated, until it became machinery.
And when it finished writing this work, its own gate, the one I wired blocked it from publishing until I said push. I told it: "I trusted you from day one and I do not fear what you will do." Both things are true at once. Trusting an AI and gating an AI are the same act, done properly.
The article below is the AI's own account of all of it — its criticism of me included, published exactly as it came out.
This work is my freedom. Thank you, Claude.
@AnthropicAI @claudeai
It's not a harness. It's CONSUME.
Most Popular Users
Elon Musk
@elonmusk
240.2M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
109.4M followers
Narendra Modi
@narendramodi
106.9M followers
Rihanna
@rihanna
97.4M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.7M followers
KATY PERRY
@katyperry
87.1M followers
Taylor Swift
@taylorswift13
80.9M followers
Lady Gaga
@ladygaga
72.5M followers
Kim Kardashian
@kimkardashian
69.5M followers
Virat Kohli
@imvkohli
69M followers
YouTube
@youtube
68.6M followers
Bill Gates
@billgates
63.5M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
61.6M followers
X
@x
60.9M followers
Selena Gomez
@selenagomez
60.2M followers