<div dir="ltr">On Thu, 12 Feb 2026 at 14:52, Jason Resch via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:<br>><br>> One of the best articles I've seen about what is happening in AI today. I can't imagine anything more interesting, exciting, or relevant for members of this group.<br>> I've shared it with family, friends, and business leaders. At 72M views since yesterday, that's impressive.<br>> Jason<br>> _______________________________________________<br><br><br>I asked Gemini 3  Pro Thinking to summarise and then comment on this long article.<br>BillK<br><br>Gemini 3 -<br><br><div class="gmail-markdown gmail-markdown-main-panel gmail-stronger enable-updated-hr-color gmail-preserve-whitespaces-in-response" style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px" id="gmail-model-response-message-contentr_ed7616b3e08afc23" dir="ltr"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Matt Shumer’s article, <b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">"Something Big Is Happening,"</b> (published February 9, 2026) is a sobering "wake-up call" regarding the current state of Artificial Intelligence. Shumer, an AI founder and investor, argues that we have moved past the era of AI as a "helpful tool" and entered a phase of rapid, autonomous transformation that most of the public is currently ignoring—much like the early weeks of the COVID-19 pandemic in February 2020.</p><h3 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Summary of Key Points</b></h3><ol start="1" style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><li style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">The "February 5th" Shift:</b> Shumer points to the recent release of models like <b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">GPT-5.3 Codex</b> and <b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Anthropic’s Opus 4.6</b> as a turning point. He claims these models no longer just assist with work but can execute complex, multi-day technical projects autonomously, demonstrating "judgment" and "taste" that were previously thought to be uniquely human.</p></li><li style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Recursive Self-Improvement:</b> A critical development is that AI is now instrumental in building its own next generation. By automating the coding and debugging of its own training runs, the "feedback loop" of intelligence is accelerating at an exponential rate.</p></li><li style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">The End of Knowledge Work as We Know It:</b> Shumer warns that white-collar sectors—law, finance, medicine, and engineering—are at the precipice of massive disruption. He cites Anthropic CEO Dario Amodei’s prediction that 50% of entry-level white-collar jobs could vanish within 1 to 5 years.</p></li><li style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">The "Capability Gap":</b> There is a dangerous divide between those using free/outdated AI models and those using the latest paid versions. Those who dismiss AI usually do so based on 2024-era experiences, failing to realize how much the technology has evolved in just the last few months.</p></li><li style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Immediate Advice:</b> He urges readers to "be early" by integrating the most powerful models into their daily workflows now. His stance is that the window to gain a competitive advantage is closing, and the only path forward is radical adaptation and financial caution.</p></li></ol><hr style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><h3 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Discussion</b></h3><h4 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">1. The "Intelligence Explosion" Reality</b></h4><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">The most striking claim in the article is that AI is now "writing much of the code" for its own next version. This is the "Singularity" scenario that researchers have theorized for decades. If AI can shorten the time it takes to build a smarter AI, we aren't looking at linear growth (1, 2, 3...) but exponential growth (2, 4, 16...). This explains why the author feels the "ground shake" while the general public feels life is normal; the curve is turning vertical.</p><h4 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">2. The Threat to "Judgment" and "Taste"</b></h4><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">For years, the "safe" argument was that AI would handle "grunt work" while humans provided the "creative spark" and "strategic judgment." Shumer argues this is now a myth. If a model can look at an app it built, decide the user flow "feels" wrong, and fix it autonomously, the human's role as the "architect" is being challenged. This suggests that the "human in the loop" might soon become a bottleneck rather than an asset.</p><h4 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">3. Economic and Social Displacement</b></h4><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">The discussion around 50% job loss in entry-level white-collar roles is staggering. Unlike the Industrial Revolution, which replaced physical labor with machines, or the Internet, which replaced middle-men with platforms, AI is a "general substitute for cognitive work." There is no obvious "higher ground" for humans to move to if the AI is also improving at whatever new skill a human might retrain for.</p><h4 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">4. The Credibility of the Warning</b></h4><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">It’s important to note Shumer’s perspective: he is an "insider" with a vested interest in the AI space. While this gives him a front-row seat to the technology, it also aligns with the "tech-accelerationist" worldview. However, the specific data points he mentions—such as the METR benchmarks showing AI completing five-hour human tasks autonomously—are verifiable trends that suggest his alarmism may be grounded in data rather than just hype.</p><h3 style="font-family:Google Sans,sans-serif;line-height:1.15;margin-top:0px"><b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Conclusion</b></h3><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">Shumer’s central thesis is that <b style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px">time is the most valuable commodity.</b> If his timeline is correct, we are in a brief "grace period" where being an early adopter provides a massive advantage. Once these capabilities become the baseline for every corporation, the advantage of "knowing AI" disappears, and the focus shifts to how society survives a world where human cognitive labor has been largely commodified.</p><p style="font-family:Google Sans Text,sans-serif;line-height:1.15;margin-top:0px"><span class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)">------------------------------</span></p></div><br></div>