CaleBrrrrrrrrrrr
@calebrrrr.bsky.social
I manage and grow communities where founders, operators, engineers, and no-code builders explore how AI can help us and we can help it.
My mission is simple: You measure it, improve it.
My mission is simple: You measure it, improve it.
Pinned
CaleBrrrrrrrrrrr
@calebrrrr.bsky.social
· Nov 14
We grew an open-source project from nothing… then had to put it into hibernation.
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)
What if your agent could decied when to remeber, like taking notes during meeting?
Traditional approach: Agent retrieves memories at EVERY turn. (wastes tokens, slow process, costs add fast
Memory-as-a-Tool: Agent calls create_memory() only when the conversation contains info worth persisting.
Traditional approach: Agent retrieves memories at EVERY turn. (wastes tokens, slow process, costs add fast
Memory-as-a-Tool: Agent calls create_memory() only when the conversation contains info worth persisting.
November 27, 2025 at 11:55 AM
What if your agent could decied when to remeber, like taking notes during meeting?
Traditional approach: Agent retrieves memories at EVERY turn. (wastes tokens, slow process, costs add fast
Memory-as-a-Tool: Agent calls create_memory() only when the conversation contains info worth persisting.
Traditional approach: Agent retrieves memories at EVERY turn. (wastes tokens, slow process, costs add fast
Memory-as-a-Tool: Agent calls create_memory() only when the conversation contains info worth persisting.
People have been tweeting a lot about AI releases like Claude Opus 3.5, Gemini 3.0, what is ChatGPT doing, etc, so let me just write something worth sharing, Chief scientist at Meta AI, Prof. is leaving Meta AI, and will be focusing on world models.
November 24, 2025 at 8:32 AM
People have been tweeting a lot about AI releases like Claude Opus 3.5, Gemini 3.0, what is ChatGPT doing, etc, so let me just write something worth sharing, Chief scientist at Meta AI, Prof. is leaving Meta AI, and will be focusing on world models.
Is it true tools and model like Claude, Jasper, Ada, Grok, and Alexa seems named the way they are named to make technology feel more approachable.
If you had an AI #Automation tool what would you #name it?
If you had an AI #Automation tool what would you #name it?
November 24, 2025 at 5:39 AM
Is it true tools and model like Claude, Jasper, Ada, Grok, and Alexa seems named the way they are named to make technology feel more approachable.
If you had an AI #Automation tool what would you #name it?
If you had an AI #Automation tool what would you #name it?
Do you think our obsession with speed will ever cease (like a poetry) but yeah I just read somewhere about microsoft super factory so it dawn to me.
Link: www.wsj.com/tech/ai/insi...
Link: www.wsj.com/tech/ai/insi...
Exclusive | Inside Microsoft’s New AI ‘Super Factory’
The tech giant is building out huge data centers among the most advanced in the world as it rushes to meet demand for AI computing power.
www.wsj.com
November 18, 2025 at 12:02 PM
Do you think our obsession with speed will ever cease (like a poetry) but yeah I just read somewhere about microsoft super factory so it dawn to me.
Link: www.wsj.com/tech/ai/insi...
Link: www.wsj.com/tech/ai/insi...
@Google DeepMind just launched #WeatherNext 2, an AI weather model that predicts global patterns up to 8× faster than traditional methods.
It generates reliable hourly forecasts and processes hundreds of possible outcomes within a minute.
It generates reliable hourly forecasts and processes hundreds of possible outcomes within a minute.
November 18, 2025 at 4:38 AM
@Google DeepMind just launched #WeatherNext 2, an AI weather model that predicts global patterns up to 8× faster than traditional methods.
It generates reliable hourly forecasts and processes hundreds of possible outcomes within a minute.
It generates reliable hourly forecasts and processes hundreds of possible outcomes within a minute.
The AI race isn't about who has the most GPUs.
It's about who can complete the most learning cycles per year.
Speed creates a compounding advantage that becomes nearly impossible to close. Here's how the major labs are optimizing for it: 🧵
It's about who can complete the most learning cycles per year.
Speed creates a compounding advantage that becomes nearly impossible to close. Here's how the major labs are optimizing for it: 🧵
November 17, 2025 at 10:33 AM
The AI race isn't about who has the most GPUs.
It's about who can complete the most learning cycles per year.
Speed creates a compounding advantage that becomes nearly impossible to close. Here's how the major labs are optimizing for it: 🧵
It's about who can complete the most learning cycles per year.
Speed creates a compounding advantage that becomes nearly impossible to close. Here's how the major labs are optimizing for it: 🧵
We grew an open-source project from nothing… then had to put it into hibernation.
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)
November 14, 2025 at 1:30 PM
We grew an open-source project from nothing… then had to put it into hibernation.
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)
Not because it wasn’t working, but because with limited funding and a tiny team, keeping it alive was pulling us under. (1)