M°M°

27.4K posts

M°M° banner
M°M°

M°M°

@Momoshi

🌸🍓S Y C | R E D A C T E D | D E 4 T H P 1 N K - 8 8

Istanbul, Turkey انضم Nisan 2010
7.5K يتبع6.2K المتابعون
M°M° أُعيد تغريده
MaryJane 🥷👑💅
MaryJane 🥷👑💅@QueenofDogecoin·
Gm💋 it’s Taco Tuesday 💕🌮
English
28
2
52
811
M°M° أُعيد تغريده
Bluu Ω
Bluu Ω@bluudmg·
fear of being included
Bluu Ω tweet media
English
9
7
56
775
M°M° أُعيد تغريده
ZARA
ZARA@HeyZaraKhan·
Become a Claude Certified Architect Here is the complete resource list in one place: Link to join: anthropic.skilljar.com/claude-certifi… Training courses: anthropic.skilljar.com (13 free courses) Cookbook: github.com/anthropics/ant… Exam Guide: share.google/0eqIbebzRMUt8K… Practice questions: claudecertifications.com (free) MCP documentation: modelcontextprotocol.io (free) API documentation: docs.anthropic.com (free) Partner Network: anthropic.com/partners (free to join) Personal Playbook someone created after the exam: drive.google.com/file/d/1luC0rn…
ZARA tweet media
ZARA@HeyZaraKhan

🚨BREAKING: Anthropic just open-sourced a powerful new framework for building AI agents and made it publicly available in a GitHub directory. It’s called “Skills” and it redefines how we work with Claude. Instead of repeating prompts, developers can now create reusable “skills” that package instructions, workflows, and logic into a single unit. A Skill = a structured capability an AI can reliably execute. For example: • Analyze datasets and generate reports • Create structured documents • Automate multi-step workflows • Execute internal business processes Each skill is: • Modular, reusable across projects • Versioned, continuously improvable • Dynamically loaded, used only when needed This solves key problems in today’s AI systems: → Repetitive prompting → Inconsistent outputs → Limited scalability The bigger shift: From: “Prompt engineering” To: “Programmable, reusable AI systems” This is a foundational step toward more reliable, production-ready AI agents. If you're building with AI, this is worth your attention.

English
45
724
4.1K
541.8K
M°M° أُعيد تغريده
Keanu Reeves
Keanu Reeves@KeanuReevetb5s·
Good morning to you all’s 💕💕💕
Keanu Reeves tweet media
English
5
993
26.3K
269.4K
M°M° أُعيد تغريده
agoston nagy
agoston nagy@_stc·
all modules are identical - built with composable, open source tools - making synchronized audio recordings over the network is just part of the system’s nature #puredata #python #bash #linux
English
20
78
731
30.4K
M°M° أُعيد تغريده
Czyzu
Czyzu@0xCzyzu·
honorary nft moment (s/o to petra) mantle boy me vs them me
Czyzu tweet mediaCzyzu tweet media
them@thembypetra

them club

English
29
2
74
1.4K
M°M° أُعيد تغريده
MaryJane 🥷👑💅
MaryJane 🥷👑💅@QueenofDogecoin·
Gm Monday time to grind 💋
MaryJane 🥷👑💅 tweet media
English
59
2
96
1.4K
M°M° أُعيد تغريده
Meech ♱.
Meech ♱.@thebulltard·
No matter how many times they try to cancel us they will never stop us but only make us stronger milady
Meech ♱. tweet media
English
15
8
105
1.8K
M°M° أُعيد تغريده
𝖍𝖊𝖑𝖎𝖔𝖕𝖍𝖎𝖑𝖎𝖆
my daily affirmations: im goated nothing is embarrassing everything is temporary it will get better i am so cool milady
𝖍𝖊𝖑𝖎𝖔𝖕𝖍𝖎𝖑𝖎𝖆 tweet media
English
14
11
75
1.5K
M°M° أُعيد تغريده
Science girl
Science girl@sciencegirl·
Techno visuals, The chemical brothers concert
English
87
744
4K
179.3K
M°M° أُعيد تغريده
Khairallah AL-Awady
Khairallah AL-Awady@eng_khairallah1·
🚨 BREAKING: Someone just open-sourced your own personal intelligence terminal. It's called Crucix. Bookmark it for later. It watches 27 live data feeds across the entire planet and alerts you when something changes. Governments and intelligence firms pay six figures for this kind of setup. This runs on your laptop for free. No cloud. No subscriptions. No telemetry. Just a single Node.js server and a Jarvis-style dashboard. What it watches every 15 minutes: → ACLED for armed conflict events worldwide → Federal Reserve economic indicators via FRED → OFAC + OpenSanctions for sanctions screening → 17 curated Telegram intelligence channels for social sentiment → Maritime AIS for vessel tracking and sanctions evasion detection → GDELT for global event tracking across 100+ languages → WHO for disease outbreak alerts → ReliefWeb for UN humanitarian data → CelesTrak for satellite constellation tracking: ISS, Starlink, OneWeb → VIX and credit spread risk gauges Every sweep computes what changed, what escalated, and what de-escalated since the last cycle. Hook up an LLM (Claude, GPT, Gemini), and it generates trade ideas based on cross-domain signal correlation. Without an LLM, a deterministic rule engine still evaluates everything. 18+ sources work with zero API keys. No setup friction. 100% Open Source. MIT License. (Link in the comments)
Khairallah AL-Awady tweet media
English
58
106
731
39.2K
M°M° أُعيد تغريده
God of Prompt
God of Prompt@godofprompt·
🚨 BREAKING: Meta AI just published a paper that redefines what “self-improving AI” means. It’s called Hyperagents, and it solves a fundamental limitation that every prior self-improving system couldn’t get past. The problem with current self-improving AI: → Systems like the Darwin Gödel Machine (DGM) can generate better versions of themselves over time → But they only work in coding, where the improvement task and the target task share the same domain → Outside coding, the self-improvement process stays fixed and handcrafted → The system gets better at tasks but never gets better at getting better What Hyperagents actually does: → Combines a task agent (solves the problem) and a meta agent (modifies both itself and the task agent) into one editable program → The modification process itself is editable, creating what the researchers call “metacognitive self-modification” → The agent doesn’t just learn to perform better. It learns to improve at improving → This works on any computable task, not just coding The results across four domains (coding, paper review, robotics reward design, Olympiad-level math grading): → Continuous performance improvements over time in every domain tested → Outperforms baselines without self-improvement or open-ended exploration → Outperforms prior self-improving systems including the original DGM → Meta-level improvements (persistent memory, performance tracking) transfer across domains and accumulate across runs That last point is the one most people will overlook. The improvements to the improvement process don’t just help in one domain. They carry over. The system builds compounding infrastructure for getting smarter, regardless of the task. This is the architectural difference between an AI that gets incrementally better at one thing and an AI that builds the scaffolding to accelerate its own progress everywhere. Meta’s team (Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, and others) essentially removed the ceiling that kept self-improving systems domain-locked.
God of Prompt tweet media
English
34
73
391
28.1K
M°M° أُعيد تغريده
alperaym
alperaym@alperaym·
Time flies ✨ Tomorrow at 6 AM UTC, SERENIA goes live on @objktcom as part of an epic collective drop featuring over 150 talented artists!
GIF
alperaym tweet media
English
7
10
20
475