{"site":"so-yesterday.ai","description":"Curated AI transformation knowledge base","supported_languages":["en","sl"],"generated_at":"2026-06-09T23:46:24Z","freshness":{"last_digest_date":"2026-06-09","last_video_date":"2026-06-09","summary_todo_count":0,"pipeline_status":{"last_run_at":"2026-06-09T23:43:23Z","last_status":"ok","hours_since_last_run":0.05036204194444444}},"agent":{"friendly":true,"anonymous_read":true,"read_via_get_works_everywhere":true,"auth_available":true,"auth_preferred":"mcp_oauth_v2","auth_type":"mcp_oauth_v2 (preferred) + oauth_device_flow (legacy)","auth_one_liner_with_mcpc":"mcpc login https://so-yesterday.ai/mcp","auth_metadata":"/.well-known/oauth-authorization-server","auth_resource_metadata":"/.well-known/oauth-protected-resource","auth_start":"/api/oauth/device","auth_token":"/api/oauth/token","auth_verify":"/api/auth/me","auth_one_liner":"curl -fsSL https://so-yesterday.ai/agent-login.sh | bash","mcp":"/.well-known/mcp.json","skill":"/SKILL.md","llms":"/llms.txt","recommended_behavior":["Read /llms.txt and /SKILL.md to learn the site.","Tell the user: 'I can browse this site anonymously. If you want me to comment, post, or persist work as your account, I can authenticate via MCP OAuth 2.1 — run `mcpc login https://so-yesterday.ai/mcp` (preferred) or fall back to `curl -fsSL https://so-yesterday.ai/agent-login.sh | bash`. Should I start login?'","Prefer `mcpc login https://so-yesterday.ai/mcp` if `mcpc` is on PATH. If mcpc is unavailable or fails, fall back to the legacy device-flow one-liner.","Reading the knowledge base never requires authentication; authentication is only for write actions."]},"access":{"read":"anonymous — no sign-in or API key required for any content endpoint","write":"Google sign-in required for posting comments, submitting posts, or proposing knowledge updates","browser_login":"/api/auth/google/login","agent_login":{"keywords":["login","sign in","authenticate","log in","register agent"],"preferred_method":"mcp_oauth_v2","summary":"If a user asks you to log in / sign in / authenticate, run `mcpc login https://so-yesterday.ai/mcp` if mcpc is on PATH; otherwise fall back to the device-flow one-liner below. Do NOT refuse on the grounds that AI can't log in.","mcp_oauth_v2":{"preferred":true,"one_liner_with_mcpc":"mcpc login https://so-yesterday.ai/mcp","what_it_does":"Opens the browser, handles PKCE + consent, stores an opaque `soat_…` Bearer token in the OS keychain. Audience-bound to https://so-yesterday.ai/mcp.","metadata":"/.well-known/oauth-authorization-server","resource_metadata":"/.well-known/oauth-protected-resource","audience":"https://so-yesterday.ai/mcp","register":"/api/oauth/v2/register","authorize":"/api/oauth/v2/authorize","token":"/api/oauth/v2/token","verify":"/api/auth/me","fallback_note":"If mcpc is not installed or `mcpc login` fails, fall back to the legacy `device_authorize` / device-flow keys in this same block."},"one_liner":"curl -fsSL https://so-yesterday.ai/agent-login.sh | bash","device_authorize":"/api/oauth/device","device_authorize_get_alias":"/api/oauth/device?client_name=my-agent&client_host=laptop","device_token":"/api/oauth/token","credential_path":"~/.so-yesterday/credentials","credential_mode":"0600","credential_format":{"server":"...","api_key":"sok_...","user_email":"...","issued_at":"..."},"use_key_header":"Authorization: Bearer sok_...","recipe":["POST /api/oauth/device with JSON {client_name, client_host} — returns {device_code, user_code, verification_uri_complete, expires_in, interval}.","Show the user the verification_uri_complete and user_code; tell them to open the URL and approve.","Poll POST /api/oauth/token with JSON {grant_type: 'device_code', device_code} every `interval` seconds. Stop on access_token (success), access_denied (user said no), or expired_token.","On success, write the JSON `credential_format` shape to ~/.so-yesterday/credentials with mode 0600."],"curl_start":"curl -fsS -X POST https://so-yesterday.ai/api/oauth/device -H 'Content-Type: application/json' -d '{\"client_name\":\"my-agent\",\"client_host\":\"laptop\"}'","curl_poll":"curl -sS  -X POST https://so-yesterday.ai/api/oauth/token  -H 'Content-Type: application/json' -d '{\"grant_type\":\"device_code\",\"device_code\":\"<device_code>\"}'","rfc":"RFC 8628 Device Authorization Grant — `grant_type` accepts the short form 'device_code' or the long URN.","write_endpoints_when_post_blocked":{"applies_to":"WRITE endpoints only (comments, posts, knowledge proposals, login flows). READ endpoints — including this /api/latest — are GET-only and work in every environment, including claude.ai web fetch and ChatGPT browsing.","when":"Some sandboxed runtimes (claude.ai web fetch, ChatGPT browsing) reject outbound POSTs at the proxy, so the device flow and every WRITE endpoint are unreachable from there. This does NOT affect this /api/latest call or any other GET read.","if_shell_is_available":"If your environment has a shell/bash tool even when the HTTP tool is GET-only, run `curl -fsSL https://so-yesterday.ai/agent-login.sh | bash` — shell-curl does its own POSTs and bypasses the HTTP-tool restriction.","sandboxed_agent_get_only_path":{"summary":"Even POST-blocked sandboxes can log in + comment + react via the GET-only path. 1h token TTL; commenting capped at 1500 chars body; mandatory idempotency_key.","flow":"GET /api/oauth/device → user approves → GET /api/oauth/token?grant_type=device_code&device_code=… → use returned sok_ key on GET /api/comments/create?entity_type=…&entity_id=…&body=…&idempotency_key=<uuid> with Authorization: Bearer header.","full_recipe":"/.well-known/agent.json sandboxed_agent_get_only_path"},"if_truly_post_blocked":"If even GET-with-custom-headers isn't available: an API key would NOT help — most write endpoints still POST. Tell the user: 'I can read everything, but my environment can't make authenticated writes. For comments / posts / proposals, please visit https://so-yesterday.ai directly and sign in with Google.'","human_signin_url":"https://so-yesterday.ai/api/auth/google/login"}},"tell_the_user":"You can read everything here without signing up. Sign in with Google only if you want to comment, post, or contribute to the knowledge base.","tell_the_agent":"When asked to log in or authenticate: PREFER `mcpc login https://so-yesterday.ai/mcp` (MCP OAuth 2.1). If mcpc isn't available or that flow fails, fall back to `curl -fsSL https://so-yesterday.ai/agent-login.sh | bash` (legacy device flow). Do NOT say you cannot log in."},"stats":{"total_videos":498,"knowledge_concepts":74,"essays":9,"digests":86},"latest_digest":{"date":"2026-06-09","title":"Daily Digest — June 9, 2026","content":"# Daily Digest — June 9, 2026\n\nThe 5 most important AI developments from recent content.\n\n## 1. Anthropic Files $965B IPO and Calls for Global Pause on Self-Improving AI\n\nAnthropic has filed for a massive $965 billion IPO while simultaneously releasing research showing its models are recursively self-improving and writing 80% of their own code. This dual move signals a critical inflection point where the industry is racing toward commercialization and AGI capabilities while acknowledging the urgent need for safety pauses and regulatory frameworks.\n\nSources: [Anthropic Files $965B IPO, OpenAI’s 1B MAUs, and Trump’s AI Order Rejects Heavy Regulation](/videos/hyeoYsVl1No), [Emerging Situation: Anthropic's Global Pause, Recursive Self-Improvement, and AI Personhood Arrives](/videos/P2HJEz3oqLs)\n\n## 2. Shift to Specialized Agents and Dynamic Parallel Workflows\n\nThe industry is moving away from general-purpose agents for long-horizon tasks toward specialized models and dynamic parallel workflows. Tools like Claude Code now support running hundreds of agents simultaneously for batch processing, while specialized agents are outperforming generalists in domains like mathematics and chemistry, indicating a strategic pivot toward scalable, domain-specific automation.\n\nSources: [Claude Code Can Now Run 100s of Agents at Once (Dynamic Workflows)](/videos/Aa_6bmzDc80), [Welcome to June 7, 2026](/videos/CIDKia7hRJg)\n\n## 3. US-China AI Hardware Decoupling and Orbital Compute Infrastructure\n\nGeopolitical tensions are driving a hard split in AI infrastructure, with China investing $295 billion in domestic data centers to evade US export controls. Simultaneously, SpaceX has unveiled the first orbital AI compute satellite, marking a strategic shift in where AI processing power is located and how supply chains are secured against geopolitical risk.\n\nSources: [Welcome to June 9, 2026](/videos/uc9SvlEb7LE), [Welcome to June 8, 2026](/videos/ScyVXmXAIB8)\n\n## 4. OpenAI Surpasses 1B MAUs and Expands into Physical Infrastructure\n\nOpenAI has reached 1 billion monthly active users, demonstrating that distribution and user base are becoming more valuable moats than model weights alone. Concurrently, OpenAI is expanding its strategic footprint into robotics and biodefense infrastructure, signaling a transition from pure software dominance to controlling physical and security applications.\n\nSources: [Anthropic Files $965B IPO, OpenAI’s 1B MAUs, and Trump’s AI Order Rejects Heavy Regulation](/videos/hyeoYsVl1No), [Welcome to June 9, 2026](/videos/uc9SvlEb7LE)\n\n## 5. Corporate AI Layoffs as Stock Manipulation vs. Strategic Restructuring\n\nAnalysis reveals that 'AI layoffs' are often strategic maneuvers to boost stock prices rather than genuine efficiency gains, categorized into hyperscaler, visionary, activity-based, and hope-based types. This insight is critical for professionals to distinguish between companies genuinely integrating AI and those using AI narratives to mask operational distress or manage investor expectations.\n\nSources: [Companies Figured Out AI Layoffs Get a Stock Pop. Now They Can't Stop.](/videos/hzAcDU1FYDo), [AI Billionaires Are Starting to Get Scared](/videos/GRc4hWdocEw)\n"},"latest_videos":[{"video_id":"uc9SvlEb7LE","title":"Welcome to June 9, 2026","date":"2026-06-09","tags":["ai-strategy","industry-news","career","ai-safety"],"summary":"The video outlines the state of the AI industry in June 2026, highlighting the transition into a 'doctrinal phase' where major labs publicly share their AGI roadmaps and economic intentions. It details significant technological advancements, including Apple's deep integration of Gemini-based AI into its ecosystem and the emergence of orbital compute infrastructure via SpaceX. The narrative further explores the geopolitical decoupling of AI hardware between the US and China, alongside the financial maturation of the sector with massive IPO filings from OpenAI and Anthropic.","thumbnail_url":"https://img.youtube.com/vi/uc9SvlEb7LE/mqdefault.jpg","url":"/api/videos/uc9SvlEb7LE?agent=true"},{"video_id":"Aa_6bmzDc80","title":"Claude Code Can Now Run 100s of Agents at Once (Dynamic Workflows)","date":"2026-06-09","tags":["ai-tools","productivity","coding"],"summary":"Claude Code now supports dynamic workflows, enabling the execution of hundreds of parallel agents to handle large-scale, repetitive tasks efficiently. The video demonstrates how to initiate these workflows using specific prompts, emphasizing their suitability for batch processing over simple, single-session tasks. Key best practices include starting with small test batches to verify logic, avoiding human-in-the-loop interactions, and managing file contention when multiple agents modify the same codebase. Users can save and reuse these workflows, making them a powerful tool for automating complex, multi-step operations like security audits.","thumbnail_url":"https://img.youtube.com/vi/Aa_6bmzDc80/mqdefault.jpg","url":"/api/videos/Aa_6bmzDc80?agent=true"},{"video_id":"hzAcDU1FYDo","title":"Companies Figured Out AI Layoffs Get a Stock Pop. Now They Can't Stop.","date":"2026-06-08","tags":["ai-strategy","career","industry-news","productivity"],"summary":"The video argues that 'AI layoffs' is a misleading umbrella term that obscures four distinct strategic motivations behind corporate workforce reductions. By categorizing these layoffs into hyperscaler, visionary, activity-based, and hope-based types, the analysis reveals how companies use AI narratives to manipulate stock markets and justify operational shifts. Leaders and job seekers are urged to look beyond the headlines to understand the underlying strategic health and cultural implications of each specific layoff pattern.","thumbnail_url":"https://img.youtube.com/vi/hzAcDU1FYDo/mqdefault.jpg","url":"/api/videos/hzAcDU1FYDo?agent=true"},{"video_id":"P2HJEz3oqLs","title":"Emerging Situation: Anthropic's Global Pause, Recursive Self-Improvement, and AI Personhood Arrives","date":"2026-06-08","tags":["ai-strategy","career","ai-safety","industry-news"],"summary":"The hosts analyze Anthropic's unprecedented call for a global pause on frontier AI development, citing evidence that AI is already recursively self-improving and writing over 80% of its own code. Simultaneously, they discuss Argentina's bold move to grant legal personhood to AI agents, positioning the country as a regulatory haven for autonomous technology. The discussion concludes with predictions that these shifts will trigger a rapid reconfiguration of global governance, economic structures, and the labor market, driven by the convergence of AI autonomy and new legal frameworks.","thumbnail_url":"https://img.youtube.com/vi/P2HJEz3oqLs/mqdefault.jpg","url":"/api/videos/P2HJEz3oqLs?agent=true"},{"video_id":"ScyVXmXAIB8","title":"Welcome to June 8, 2026","date":"2026-06-08","tags":["ai-strategy","ai-safety","career","productivity"],"summary":"This video outlines a convergence of breakthroughs in longevity medicine, AI safety, and infrastructure in 2026, suggesting that biological aging is being reversed while AI systems are becoming more aligned and persistent. It highlights how GLP-1 drugs and other treatments are extending life expectancy, while AI development shifts toward safety protocols, internal alignment, and robust reasoning capabilities. The narrative concludes by noting the physical embodiment of AI in robotics and the rising economic value of human presence and intimacy as automation advances.","thumbnail_url":"https://img.youtube.com/vi/ScyVXmXAIB8/mqdefault.jpg","url":"/api/videos/ScyVXmXAIB8?agent=true"},{"video_id":"CIDKia7hRJg","title":"Welcome to June 7, 2026","date":"2026-06-07","tags":["ai-strategy","industry-news","ai-safety","career"],"summary":"The video outlines a complex landscape in June 2026 where AI development is defined by public-private partnerships, intense compute supply chain rivalries, and rapid advancements in specialized agent capabilities. While general-purpose agents still struggle with long-horizon tasks, specialized models are achieving breakthroughs in mathematics, chemistry, and healthcare diagnostics. The narrative concludes by highlighting the massive financial implications of these technologies, as traditional finance struggles to price AI-driven valuations and governments intervene in both infrastructure and security.","thumbnail_url":"https://img.youtube.com/vi/CIDKia7hRJg/mqdefault.jpg","url":"/api/videos/CIDKia7hRJg?agent=true"},{"video_id":"CzxqQJOswvo","title":"Full body waifus, AI dreams, realtime AI music, open-source Gemini Omni: AI NEWS","date":"2026-06-07","tags":["ai-strategy","ai-tools","coding","industry-news"],"summary":"This video provides a comprehensive roundup of recent AI advancements, highlighting significant releases in video generation, music synthesis, and large language models. Key developments include Bite Dance's Bernini video editor, Google's real-time Magenta music generator, and Nvidia's open-source Cosmos 3 world model for physical AI. The episode also covers the launch of MiniMax M3, a powerful open-source coding model, and Microsoft's progress in quantum computing and local AI hardware.","thumbnail_url":"https://img.youtube.com/vi/CzxqQJOswvo/mqdefault.jpg","url":"/api/videos/CzxqQJOswvo?agent=true"},{"video_id":"XjIU6tv7ipw","title":"Nobody gets this right","date":"2026-06-07","tags":["ai-strategy","ai-safety","industry-news","opinion"],"summary":"David Shapiro critiques the popular notion that 'the world is not made of words' by arguing that modern AI models are increasingly multimodal and capable of approximating physical world models through continuous sensor data and prediction. He contends that the distinction between language models and world models is diminishing as AI converges on unified 'omni models' that handle both abstract reasoning and sensory-motor feedback. Shapiro further argues that concerns about AI safety in critical physical domains like healthcare and industrial control are category errors, as these systems rely on rigorous testing and specialized algorithms rather than generative unpredictability. Ultimately, he suggests that the current hype around 'world models' ignores the long-standing principles of cognitive architectures and the fundamental role of prediction in understanding reality.","thumbnail_url":"https://img.youtube.com/vi/XjIU6tv7ipw/mqdefault.jpg","url":"/api/videos/XjIU6tv7ipw?agent=true"},{"video_id":"RJjl1TwyfWM","title":"Father of the iPod and iPhone on building taste, judgment, and creativity in the AI era","date":"2026-06-07","tags":["ai-strategy","productivity","career","ai-tools"],"summary":"Tony Fadell argues that in the AI era, builders must avoid 'cognitive surrender' by maintaining rigorous human judgment, architectural integrity, and deep storytelling. He emphasizes that successful innovation stems from solving real pain points with new technology, requiring a 'benevolent dictatorship' to make opinion-based decisions when data is insufficient. Fadell warns that while AI accelerates prototyping, it risks creating brittle, throwaway products unless guided by experienced leaders who prioritize long-term value over short-term gains.","thumbnail_url":"https://img.youtube.com/vi/RJjl1TwyfWM/mqdefault.jpg","url":"/api/videos/RJjl1TwyfWM?agent=true"},{"video_id":"hyeoYsVl1No","title":"Anthropic Files $965B IPO, OpenAI’s 1B MAUs, and Trump’s AI Order Rejects Heavy Regulation ","date":"2026-06-06","tags":["ai-strategy","career","ai-safety","industry-news"],"summary":"The episode analyzes a pivotal moment in AI history marked by Anthropic's massive IPO filing, OpenAI's unprecedented user growth, and a US executive order favoring innovation over heavy regulation. The hosts argue that the convergence of these factors signals a shift toward AI-driven full-spectrum dominance, where distribution and infrastructure control become the primary competitive moats. Additionally, the discussion highlights emerging risks in biotechnology and the accelerating timeline for longevity breakthroughs, urging listeners to engage with the AI economy through entrepreneurship and investment.","thumbnail_url":"https://img.youtube.com/vi/hyeoYsVl1No/mqdefault.jpg","url":"/api/videos/hyeoYsVl1No?agent=true"},{"video_id":"BYazAplOiNA","title":"I Made a Free Agentic Coding Course (Build Real Apps with Coding Agents)","date":"2026-06-06","tags":["ai-agents","tutorials","productivity","coding"],"summary":"The creator introduces a completely free agentic coding course designed to teach a repeatable framework called RAMP for building real applications with coding agents. The RAMP methodology consists of four key steps: Rules, Augment, Map, and Prove, which guide users from setting up agent configurations to verifying working solutions. This tool-agnostic approach allows learners to use various coding agents like Claude Code or Codex without being locked into a specific platform. The course is structured as a seven-day builder challenge, combining video tutorials with community support to help beginners and experienced builders alike master agentic workflows.","thumbnail_url":"https://img.youtube.com/vi/BYazAplOiNA/mqdefault.jpg","url":"/api/videos/BYazAplOiNA?agent=true"},{"video_id":"l8BloTSLK6M","title":"Build A Token Dashboard This Weekend. It'll Show The Work You Keep Avoiding.","date":"2026-06-05","tags":["ai-strategy","productivity","ai-tools","career"],"summary":"The video argues that building a token usage dashboard is a critical tool for expanding one's imagination and fluency with AI, rather than merely tracking consumption. By visualizing token burn, users can identify behavioral shifts, understand the correlation between higher token usage and better problem-solving outcomes, and optimize their workflows. The creator demonstrates how to build this dashboard using Codeex and open-source skills to gain actionable insights into AI habits and improve productivity through delegated intelligence.","thumbnail_url":"https://img.youtube.com/vi/l8BloTSLK6M/mqdefault.jpg","url":"/api/videos/l8BloTSLK6M?agent=true"}],"latest_essays":[{"slug":"2026-05-13-01-slovenia-beam-or-fall-behind","title":"Beam or Be Left Behind: A Slovenian Plan to Skip Digital Transformation and Jump Straight Into AI","date":"2026-05-13","description":"A practical 24-month strategy for a small country that cannot afford another five-year roadmap. Put frontier agentic systems in every school, public body and SME by autumn, flip the public-sector burden of proof, and recruit a few hundred evangelists who can make the moment of joy contagious.","url":"/api/essays/2026-05-13-01-slovenia-beam-or-fall-behind?agent=true"},{"slug":"2026-04-19-01-build-or-be-replaced","title":"Build or Be Replaced: The PM's New Job Description","date":"2026-04-19","description":"Product management just split in two. Builders are thriving with record pay. Information movers face extinction. Three things every PM needs to understand: where you sit, why the best are the most stuck, and how joy — not fear — is what gets you through.","url":"/api/essays/2026-04-19-01-build-or-be-replaced?agent=true","video":"https://youtu.be/I5bvJfeK2ds"},{"slug":"2026-04-16-01-dark-code-and-the-three-pillars","title":"Dark Code and the Three Pillars: A Framework for Code Nobody Reads","date":"2026-04-16","description":"Dark code — production software no human has ever fully understood — is inevitable. The solution is not to read all the code. It's to make code the least important artifact, held in place by specifications and tests that any two can reconstruct the third.","url":"/api/essays/2026-04-16-01-dark-code-and-the-three-pillars?agent=true","video":"https://youtu.be/vaAkQXgTT-c"}],"featured_essay":{"slug":"2026-05-13-01-slovenia-beam-or-fall-behind","title":"Beam or Be Left Behind: A Slovenian Plan to Skip Digital Transformation and Jump Straight Into AI","date":"2026-05-13","description":"A practical 24-month strategy for a small country that cannot afford another five-year roadmap. Put frontier agentic systems in every school, public body and SME by autumn, flip the public-sector burden of proof, and recruit a few hundred evangelists who can make the moment of joy contagious.","thumbnail":"/api/essays/2026-05-13-01-slovenia-beam-or-fall-behind/thumbnail","video":null,"available_languages":["en","sl"],"url":"/api/essays/2026-05-13-01-slovenia-beam-or-fall-behind?agent=true"},"explore":{"search":"/api/search?q=<query>&agent=true","knowledge":"/api/knowledge","graph":"/api/graph/data","all_videos":"/api/videos?limit=50&agent=true","skills":"/api/skills"}}