0xRafy

Anthropic released a full session on how to build with Opus 4.6: "I couldn't sleep. this is the moment that's going to change everything" • 00:00 - sub-agents, context compaction, adaptive thinking - Opus 4.6 • 5:39 - what's improved since Opus 4.5 • 11:55 - how Opus 4.6 catches data - demo • 35:27 - Opus 4.6 builds a full financial model from scratch • 43:26 - how to know if a new model actually makes your product better this 1-hour watch will save you $500 on paid courses about building AI products with Opus 4.6 Watch it today, then read the article below on how to build efficient agentic loops from scratch.

@PaulTorresnxi 100%. tools are changing faster than most people realize

@0xRafy that's really interesting to see how AI is changing the way we approach coding and engineering

Anthropic and Boris Cherny just dropped a full session on how Claude Code is replacing traditional engineering: • 00:00 - how Boris went from 5% to 100% AI-written code and deleted his IDE • 05:22 - how Boris runs 5 Claude Codes in parallel • 07:21 - Claude for people who never opened a terminal - CoWork • 38:32 - how to make Claude 10x more productive with skills • 49:00 - code modernization demo - COBOL to Java in minutes this 1-hour watch will replace 10 paid courses on Claude Code. Watch it today, then read the article below on how to build efficient agentic loops from scratch

@Alexvx_nft yeah, Boris keeps making alpha moves haha

@0xRafy Deleted his IDE. Bold move. 5 parallel agents running wild.

@de1lymoon these sessions with Andrew Ng are so alpha, thanks for sharing !

Google Brain co-founder Andrew Ng explained the roadmap for building AI agents in 5 simple steps: 00:00 - Intro to AI agents and prompting 02:22 - Context and memory for better agent behavior 09:22 - Code execution and building real apps 21:12 - Why agentic workflows beat one-shot prompting 34:07 - Reflection, tool use, planning and multi-agent collaboration 51:24 - The rise of AI agents and agentic reasoning This is not another AI tools tutorial. It is a practical roadmap for building useful agents: context, memory, code execution, app building, reflection, tool use, planning, and multi-agent workflows. Watch it today, then read the article below to learn how to build AI agents that actually work.

@0xCodez glad to share this, enjoy the watch bro !

@0xRafy Wow. New session with Boris. Really amazing watch bro. Thanks for the share

@de1lymoon ye bro, every single session with Boris is aplha

@0xRafy Banger video

@misat0x sure bro, but better try it asap haha

@0xRafy saved for when i have a quiet afternoon

Anthropic just dropped a full guide on how to actually use Fable 5: • 00:00 - Fable 5 - what the new models can do • 18:03 - how to build Managed Agents with Fable 5 • 28:01 - next-level developer experience • 41:42 - autonomous agents with Fable 5 • 1:34:00 - run agents without burning money This 2-hour watch will replace 10 paid courses on building agents. Watch it today, then read the article below on how to build self-improving agents with Fable 5

@0xWast3 yep, straight from the article. easy to miss if you don't read the whole thing

@0xRafy The same setup is described right in the article

GTA 6'S WATER TRACKS TIDE LEVELS OVER TIME, AND ALLIGATORS TREAT THAT WATER AS A GATEWAY INTO YOUR NEIGHBORHOOD The trailer already shows a wooden dock with a dark, saturated band sitting above the current waterline, a mark left behind as the tide receded earlier. That single detail means the game is tracking real water levels rather than just rendering a static ocean texture underneath everything. Rain works the same way, pooling into low spots on the highway and forming temporary lakes instead of just wetting the pavement for show. Alligators move through that same wet environment freely, and the trailer shows one crawling out of a residential swimming pool while another gets caught wandering into a gas station. If water state actually persists across the map, wildlife encounters near it stop being scripted moments and start being a byproduct of wherever the tide happens to be that day. See the tide and wildlife details frame by frame below👇

@Serantych exactly, cost optimization is an underrated skill

@0xRafy solid pull. running agents cheap is the skill nobody teaches

@vartekxx ye bro, I am testing fable 5 now, so yep, very useful

@0xRafy that’s so relevant now, thanks for sharing !

@L1vsun damn how old is this guy ? real legend

by the time a strategy shows up on twitter, a $3B fund ran that backtest 14 months ago they deployed, extracted the edge, quietly moved on signal isn't dead because it "stopped working" - it's dead because someone already drained it it has a name: alpha decay. every factor research paper measures it half-life of a standard momentum signal went from ~24 months in the 90s to under 9 months by 2015 signal wasn't bad. capital is just faster than information reaches you actual job at a quant desk isn't finding edges it's running a portfolio of signals with known decay curves and rotating out before the premium is gone retail: does this still work? quant: how far into the decay curve are we already? different question entirely. Save it question gap isn't skill or code you've been measuring the wrong thing from day one

@0xRicker Wow bro, this is truly an alpha watch on loop and harness engineering - thanks for the share.

Ex-Google AI Agent Architect just launched a full course on " Harness, Loop, AI Agent Memory system" 90% AI agents are wasting 60%+ of their tokens wrong 00:00 - Ai Agent Memory 12:06 - Harness, Loop 31:18 - Ai Agent System This 50-minute will replace 10 paid courses and guides on Harness and Looping Watch it today, then read how to build proper agent loops in the article below

@0xLagosaur damn mate, what a great breakdown, thanks for the share. booked for myself

you keep asking if it's conscious that's the wrong thing to be watching Anthropic didn't find a mind in there they found the spot where, it decides what to keep from you the risk was never whether it thinks it's whether it can hide what it thinks and until now you had no way to check

@0xchromium damn bro, what a great fireside chat ! real legend. thanks for the share

Boris Cherny: "I just have a bunch of these loops running at any time" he built Claude Code, and this is him at Sequoia's AI Ascent 2026, explaining how he actually runs it day to day: 0:55 - Claude Code crowd check, how many people already run it daily 6:50 - Boris personal workflow 8:51 - future teams, when the loop replaces manual review a loop isn't just the agent trying again, it's closer to a colleague that checks its own work before any of it reaches you the article breaks that same loop down into 4 parts you can actually build yourself full session is shown below

@0xCodez true, love that they're making it free

@0xRafy Wow fresh course on Fable5 by Anthropic. Real chad !