Misaq

116 posts

Misaq banner
Misaq

Misaq

@BinaryCoder101

Building...

127.0.0.1 Tham gia Temmuz 2024
236 Đang theo dõi55 Người theo dõi
Tweet ghim
Misaq
Misaq@BinaryCoder101·
Wrapped up my new Agentic AI project It uses Gemini function calling to: - inspect directories and files - read and write code - execute Python scripts in a sandboxed workspace - loop through tool calls until a task is completed Mostly built it to understand how tool-calling agents, context management, and agent loops work under the hood. Check it out: github.com/binaryCoder-10… #AgenticAI #LLM #BuildInPublic #100DaysOfCode
English
2
0
5
849
Misaq
Misaq@BinaryCoder101·
@Francois_bth @X Followed 👍... I'm also planning to build something like this up next...
English
0
0
0
3
Francois Botha
Francois Botha@Francois_bth·
@BinaryCoder101 @X Let's connect! I'm building ombutocode.com - open source ai coding factory - guides you through requirements and architecture and automates building, testing and evaluation. Speed up up your dev process!
Francois Botha tweet media
English
1
0
1
4
avrl ☘
avrl ☘@avrldotdev·
Remember the times when devs utilised each byte of the RAM? Pfft, today Slack alone eats 2GB. VSCode takes 4GB & don't get me started on Claude Code & it's hunger for memory. We replaced optimization with "just add more RAM & CPU." The irony is that 2026 is shipping the most resource-hungry software while hardware prices keep climbing. Hardware got better but software got lazy faster.
English
12
3
36
1.3K
Misaq
Misaq@BinaryCoder101·
@avrldotdev And people went to the moon with 4kb of RAM... Either they were insanely optimal in the past, or the conspiracy theories are true 🙂
English
0
0
0
8
Arman
Arman@armanzeroeight·
@BinaryCoder101 @X DemoMode (demomode.app), makes your product demos 5x better. right in the devops/cloud space you mentioned. let's connect
English
0
0
0
15
Starbox-Group
Starbox-Group@Starboxgroup·
@BinaryCoder101 @X Here's what I built: • RAG gives agents knowledge. • MCP gives agents tools. • Snipara Companion gives agents continuity. Git-style workflows for long-running AI projects. Status. Brief. Handoff. Resume. Open source: github.com/Snipara/snipar…
English
1
0
1
16
Juan Pablo Moreno
Juan Pablo Moreno@master_jpma·
@BinaryCoder101 @X Currently building AI agents for companies. The goal: - qualify leads - schedule appointments - automate conversations - and feel more human than a chatbot. Launching soon 👀. I’m following you... Can I get an FB as well?🤝
English
1
0
1
17
Misaq đã retweet
Aman
Aman@Amank1412·
A senior Google engineer quietly dropped a 400+ page guide on AI systems free. It’s called Agentic Design Patterns. Most paid AI courses suddenly feel unnecessary.
Aman tweet media
English
3
8
75
4.4K
Misaq
Misaq@BinaryCoder101·
@t_Duches Be like Bob... Avoid unnecessary evil eye...
Misaq tweet mediaMisaq tweet media
English
0
0
0
14
Adesewa
Adesewa@t_Duches·
Men are so private online. A guy could be moving to another country or having his first child, and he’d still only post a random football score on his story.
English
1.2K
14.1K
121K
2.4M
Aadit Sheth
Aadit Sheth@aaditsh·
Wait. Google is paying SpaceX $920 million per month for GPUs? Google. The company that builds its own TPUs. That runs one of the largest cloud infrastructures on earth. Is renting 110,000 Nvidia GPUs from a rocket company. I'm honestly not sure what to make of this. Either Google's AI compute needs have gotten so massive that even they can't build fast enough. Or SpaceX has built something in AI infrastructure that nobody was paying attention to. Or both. $920M a month. $30B over the contract. Whatever is happening behind the scenes at these companies is moving way faster than what we see publicly.
Sawyer Merritt@SawyerMerritt

SpaceX has just announced that they have entered into a $920 million per month agreement with Google to provide compute capacity, according to a new filing. "On June 5, 2026, we entered into a Cloud Service Agreement with Google with respect to access to compute capacity. The customer has agreed to pay us $920 million per month from October 2026 through June 2029, with capacity ramping up through September at a reduced fee. The compute capacity provided includes approximately 110,000 NVIDIA GPUs, CPUs, memory, and other related components. After December 31, 2026, the agreement may be terminated by either party upon 90 days' notice. The customer will retain ownership of, and intellectual property rights in, its content, Al models, and related data."

English
655
497
5.9K
1.1M
Misaq
Misaq@BinaryCoder101·
@aaditsh Why does it sound pretty much like this?
Misaq tweet media
English
1
1
27
1.3K
Misaq
Misaq@BinaryCoder101·
@ajeetprssingh The economy is becoming gig based... "Sarkari babu" minded folks with no concern for upskilling will be having a very hard time by 2030...
English
0
0
0
41
Nawaz
Nawaz@NawazHosain·
Hey @X I'm looking to #connect with people interested in : - Frontend - Backend - Full stack - DevOps - Ai/ML - Data Science - Freelancing - Startup - Tech Let's grow together🚀 Say Hi
English
68
2
53
2.2K

Khám phá

@Francois_bth @X @_Gowtham_codes @avrldotdev @gmax_digital_ @armanzeroeight @yarasekou2 @Starboxgroup