meejam

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

@Jjcruz2 Gaslight pa salot na DDS. E yung motion? Para makaparticipate parin ang puganteng si Bato, may mga kasong at pwedeng makulong na si Jinggoy, Joel, Chiz at Marcoleta? Para manatili as SP si boy 10k? Yan ang self-interest.

Isinasangkalan mo pa ang mga Pilipino e purong pansariling interest nyo lang din nman sa minority yang walk out nyo! Debate at botohan ang proseso nyan e bakit kayo nanakbo? Hilig nyo umarte. Mga iyakin! 🥴

@brentoy143 @YesYesYo13 Bobo naman talaga hahaah

@YesYesYo13 At lahat sila nagsasabi na bobo ang mga DDS. SAME script

Mayroon at least 300 trolls ang Palasyo. Why do I say this? Lahat ng trollaloslos, ang followers consistent at 300 something. All of them. That's around 300 trolls being paid for by government funds.

this guy literally put a full AI engineering curriculum on GitHub and made it 100% FREE 🤯 435 lessons. 20 phases. 320 hours. The rule that makes this curriculum completely different: Every algorithm gets implemented from raw math before a single framework gets imported. You build the backprop. You build the tokenizer. You build the attention mechanism. By the time you use PyTorch, it’s just a shortcut for something you already know how to code from scratch. It spans four languages: → Python for ML pipelines → TypeScript for agent tooling → Rust for performance-critical components → Julia for numerical computation And the best part? Every single lesson ships something you can actually use. You walk away with fully deployable prompts, SKILL. md files, agents, and MCP servers. The curriculum scales from foundational math all the way up to autonomous agent swarms and production infrastructure. Free, open-source, and MIT licensed. repo in 🧵↓

@urpoliticalchar Claiming Dutae’s statements are rhetorical is just the same as when you say Davao is like Singapore.

Not Journalism When Duterte “challenged” the ICC to take him and Bato said he’d go with him, both statements were clearly rhetorical. Duterte has been consistent from day one: he never recognized the ICC’s jurisdiction. He has always maintained that any accountability must happen in Philippine courts, under Philippine law, by Filipinos. There was never a genuine “promise” to surrender to the ICC, because Duterte never accepted its authority in the first place. So asking Bato why he won’t “fulfill” his promise to join Duterte in the Hague is pure intellectual dishonesty. Jessica Soho’s interview wasn’t journalism. It was an attempt to manufacture drama and ride the wave of the Senate attack.

Anthropic pays $750,000+ a year for engineers who know how to build LLMs from scratch. Stanford just released the exact lecture that teaches it - 1 hour 44 minutes, free, straight from CS229. Bookmark this & give it 2 hours today. It'll teach you more about how ChatGPT & Claude actually work than most people at top AI companies learn in their entire careers.

@urpoliticalchar Eto na naman example na salot ang DDS. Words are very powerful and this motherfucker use it to gaslight to the detriment of the Philippine society.

I expect the PNP to stand by Bato if the ICC moves to arrest him. If they simply allow it to happen, they risk setting a dangerous precedent where law enforcement actions themselves can later be treated as crimes. Once police officers begin fearing prosecution for carrying out their duties, hesitation replaces enforcement, and criminals exploit that vacuum. States collapse that way, slowly at first, then all at once.

🚨 Google acaba de liberar sus skills oficiales para agentes de IA. Ha publicado 13 skills compatibles con Claude Code, Cursor, Copilot y otros agentes. Permiten que los agentes puedan ejecutar tareas avanzadas y automatizar flujos de trabajo complejos. Es gratis y open-source 👇

@mirasga Anong benepisyong makukuha ng Pinoy kung allowed? Sa tagal na absent si Bato, magsabi ka nga ng contribution nya sa lawmaking. Bugok ka ba? Sabagay anong aasahan sa DDS?

The Judiciary allows VCH. Tapos bawal adopt ng modern technologies ang Senate?

@YesYesYo13 @manayleila Saan? Transparent naman sya na nagrequest sya nyan. Gumagawa ka na naman ng issue, nanggagasulito (gaslight) ka naman e.

Niloloko mo na naman kami, @manayleila . Warrants yun ng Muntinlupa RTC, whose jurisdiction was sustained by the SC. But you asked for two days pa sa loob ng Senate. I was there outside.

KIMI FOUNDER JUST DROPPED A 40-MINUTE MASTERCLASS. The exact architecture behind a $20B valuation — there's no faster way to learn how to build AI agents right now. Bookmark this for the weekend. 40 minutes. zero fluff. from the person who built it. Optimization → Linear Attention → Sub-Agents → Open Systems → Cash

How to become dangerously good at AI without wasting 1000+ hours. No useless tutorials. No fake AI gurus. No information overload. I spent weeks filtering the internet so you don’t have to. Here’s the ultimate AI learning stack for: • LLMs • AI Agents • MCP • Prompt Engineering • RAG • AI Engineering • Vector Databases 🧠 Videos LLM Introduction youtube.com/watch?v=zjkBMF… LLMs from Scratch youtube.com/watch?v=9vM4p9… Agentic AI Overview (Stanford) youtube.com/watch?v=kJLiOG… Building & Evaluating Agents youtube.com/watch?v=d5ElIX… Building Effective Agents youtube.com/watch?v=D7_ipD… Building Agents with MCP youtube.com/watch?v=kQmXtr… 🗂️ Repositories Microsoft AI Agents for Beginners github.com/microsoft/ai-a… Prompt Engineering Guide github.com/dair-ai/Prompt… Hands-On LLMs github.com/HandsOnLLM/Han… Made With ML madewithml.com LLM Course github.com/mlabonne/llm-c… 📚 Guides Google Agent Whitepaper kaggle.com/whitepaper-age… Building Effective Agents by Anthropic anthropic.com/engineering/bu… OpenAI Practical Guide to Agents platform.openai.com/docs/guides/ag… 📖 Books Building LLMs from Scratch manning.com/books/build-a-… The LLM Engineering Handbook oreilly.com/library/view/l… AI Engineering oreilly.com/library/view/a… 📄 Papers ReAct arxiv.org/abs/2210.03629 Toolformer arxiv.org/abs/2302.04761 Generative Agents arxiv.org/abs/2304.03442 🎓 Courses HuggingFace Agents Course huggingface.co/learn/agents-c… MCP with Anthropic anthropic.com/engineering Bookmark this. You’ll need it sooner than you think.

Godfather of AI: "If you sleep well tonight, you may not have understood this lecture." This 47-minute lecture is the best thing I saw about AI in the last few months. It will definitely help you understand how it actually works and where it's going. Geoffrey Hinton built the neural networks behind every AI alive, then quit Google to warn the world about it. The part nobody wanted to hear: > AI is already developing abilities its creators didn't intend > in most cognitive tasks it's already ahead of us > the question is no longer if it surpasses us but when > the only decision left is which side of that line you're on Right now the average person opens Claude, types something, gets an answer, closes the tab. They think they're using AI. they're using maybe 10% of it. I went through his entire lecture, built a practical system from what he was describing. 18 steps to actually use Claude the right way, with copy-paste prompts that work today. Full guide in the post below.

@LakasNgTimog Konti nalang madadagdagan na ng karton

Removing Bato from the equation will allow BBM & his cohorts a chance to retake the senate presidency and successfully impeach Inday. But they underestimate the Filipino people. We will support whoever the Dutertes endorse. You take one down, countless more will replace them.

Supertonic just killed ElevenLabs. A text-to-speech model that runs entirely on your device. No cloud. No API key. No per-character pricing. 2,700 GitHub stars. 100% open source. MIT licensed. The numbers are wild: → 167x faster than real-time on an M4 Pro → Only 66M parameters → 1,263 chars/sec vs ElevenLabs Flash at 287 → 1,048 chars/sec vs OpenAI TTS-1 at 55 → Runs on a Raspberry Pi. Runs on an e-reader in airplane mode. Reads currency, dates, phone numbers, and technical units correctly without preprocessing. ElevenLabs fails these. OpenAI fails these. Gemini fails these. Supports 11 platforms and 5 languages. Chrome extension turns any webpage into audio in under a second. I've watched on-device models lose to cloud APIs for years. This one doesn't lose. The cloud TTS business just got cooked.

@TishaCM This. Another post that proves it’s more embarrassing to be a DDS than soiling your pants for the public to know.

The big difference between Padilla and Pangilinan isn’t just the millions of votes separating them. Robin earned his seat on his own merits, while the other is a career politician with so-so track record who capitalized on his megastar wife’s popularity to stay relevant. And yet, like a true-blue Dilawan, Pangilinan treats Robin with a level of disdain and condescension that was on full display in the plenary. In the eyes of the electorate, a man with a historic 27-million-vote mandate deserves the same respect as a self-styled “political elite” expects for himself.

@Felix1345554 @Crissy41203561 @deej_lucas @TrillanesSonny Mas nakakahiya na talagang matae sa salawal keysa maging DDS haha.

@meejam @Crissy41203561 @deej_lucas @TrillanesSonny libre mangarap. President Sara is coming! hahaha sino nga ulit manok nyo? Si Risa??? bwahahahahha

Anong pinagsasabi ni Alan Cayetano na wala pang naa-aresto sa loob ng Senate? Eh, ano ‘to? Back in 2018, Makati RTC issued a warrant against me for rebellion and it was served by the PNP while the Senate was in session. The arresting PNP personnel read to me the Miranda rights while I was at the Executive Lounge beside the Senate Session Hall. Sumama ako sa mga pulis na nag-aresto sakin. Video courtesy: Rappler

Chinese researchers have developed the best shortest-path algorithm in 41 years. Dijkstra’s Algorithm has been the undefeated king of the shortest path for over 40 years. Whether you’re using Google Maps, booking a flight, or routing internet packets, Dijkstra is the engine running in the background. Since 1984, textbooks have taught that its efficiency was hit by a “sorting barrier.” To find the shortest path, you have to sort the points by distance. And sorting has a mathematical floor you can’t cross. Until now. A research team from Tsinghua University just published a paper that shatters the 41-year-old record. They proved that Dijkstra is not optimal. By combining the logic of the Bellman-Ford algorithm with a revolutionary “recursive partial ordering” method, they figured out how to find the path without fully sorting the nodes. The results are a massive shift in theoretical computer science: - the first deterministic improvement to the Single-Source Shortest Path (SSSP) problem since 1984 - a new time complexity of O(m log^(2/3) n), officially beating the long-standing O(m + n log n) limit - on massive sparse graphs (like the web or global logistics), this means finding the best route significantly faster than previously thought possible For four decades, the greatest minds in algorithms believed this limit was absolute. Last year, even the legendary Robert Tarjan won an award proving Dijkstra was “optimally efficient” at sorting distances. Tsinghua’s answer? Stop sorting. The world’s most settled problem is suddenly wide open again. If we can break a 40-year-old law in basic graph theory, what other “impossible” speed limits are waiting to be crushed?

40% of the code Claude writes for you is wasted. you're paying for the rewrite. a 65-line markdown file fixes it. 120,000 developers have starred it. the author tested it on "30 codebases over 6 weeks" and reported a mistake rate drop from 41% to either 11% or 3% depending on whether you read the headline or the body. the irony is that the article is right. CLAUDE.md is the most under-leveraged file in your stack. 65 lines of behavioral rules outperform a 4,000-token preferences dump. "be careful" is useless. testable imperatives are gold. "be senior" doesn't work Claude already thinks it is. the 4 rules that ship the most leverage: / state assumptions, never guess silently / minimum code, nothing speculative / surgical changes, don't refactor adjacent code / define success, loop until verified compliance: ~80%. mistake rate: from ~40% to single digits. no human caught the contradicting numbers in the title. nobody had to.

@Felix1345554 @Crissy41203561 @deej_lucas @TrillanesSonny 2 years? Dutae himself spent 6 years.

@Crissy41203561 @deej_lucas @TrillanesSonny bakit naman pag aksayan ng oras ni President Sara si Trililing? Eh wala naman yan position hahaha. Asong ulol na naka tanghod lang kay Bangag. hahah