#Expert opinion

AIHarrison Chase argues that every agent harness requires a durable runtime, citing pi-durable as an example alongside deepagents built on LangGraph. The post frames durable execution as a basic requirement for agent systems rather than an optional feature. Pi 1.0 shipped with Pi Durable, which the referenced @pidotdev post invites users to customize.

AIRollouts account for most of RL's compute cost, and splitting them from training across separate engines can introduce numerical mismatches. In MoE models, such mismatches can even route tokens to different experts. Fireworks says it co-builds both engines so training stays fast and consistent.

AIBoris Power, who is listed as associated with OpenAI, posted only that he is excited for the next transportation revolution, without naming a product, company, or figures. The post links to Bryan Caplan's piece on rideshare economics, which estimates an equilibrium price of about $2 an hour for autonomous vehicles even when they sit empty half the time.

AIThe author jokes about founding a consulting firm that would use agents for work, Griffin for meetings, and Griffin for interviews to fill remote roles. They then question whether remote engineers and consultancies would still be needed if that became reality. The quoted Tavus post says Griffin passed a video Turing test with 48% of live interlocutors believing it was human.

AIDatabricks CEO Ali Ghodsi highlighted the automation of marketing campaigns and promoted a talk by Tasso at Braze. The background post says marketing agents need real-time customer and business context, which Databricks' CustomerLake is positioned to provide.

AICline says two of its largest tasks in the last 30 days each processed 9B tokens, costing about $8,500 on Claude Opus 5 versus about $300 on DeepSeek V4 Pro. The post says that is roughly 30x cheaper for the same token count, letting users run large-horizon work without spending thousands or waiting on limit resets.

AIarXiv has introduced stricter rate limiting for all submitters to fairly distribute moderator time. The post links this move to Vibe research, where turning ideas into papers is easier, while noting that standards for judging research output have not kept pace.

AIHarvard physicist Matthew Schwartz argues that LLMs are poorly matched to science when used as human-style collaborators, so he built a toolkit for exact quantitative calculations. Working with Claude, the approach surfaced connections to ecology, population genetics, and a dozen other fields, with domain experts steering it toward interesting questions.

AIFrançois Chollet argues the key difference between base LLMs and modern LRMs is a shift from transductive answer prediction to inductive prediction of the program or reasoning chain behind an answer. He says this enables test-time induction and substantial fluid intelligence in LRMs, which he claims base LLMs largely lack. He cites ARC 1 results: base LLMs remain around 10-15%, while LRMs of the same size or smaller saturated the benchmark in 2025.

AIEmber-1, built on the Kimi K3 base model, is reported by @kickingkeys to cost about 20% less and use about 36% fewer reasoning tokens across 124 test prompts. The same tester says it runs about 2x faster, while the source's painting examples show its own expressive style.

AIFireworks AI's Ember-1 produced a near-identical composition to Kimi K3 on the same JavaScript painting prompt, according to Sophia Yang. Ember-1 used 9x fewer thinking tokens and ran 4x faster at half the cost.

AIGuillermo Rauch argues that the future is verification engineering, spanning proofs, end-to-end tests, benchmarks, and linters. He expects some of these tests to be deterministic and others agentic, and he says the approach looks great. The quoted post introduces e2e, an open-source agentic testing framework that mixes deterministic and agentic APIs and runs locally or in CI.

AICloudflare has open-sourced Clef and Clef-Flash, its first homegrown decision models, now available on Workers AI. Harrison Chase praised the release as an open-weights entrant and argued that agent harnesses should be able to swap their decision model as easily as their main model.

AIOpenAI's Vaibhav Srivastav posted a short "we're so back" message, linking a demo of "dots" that the OpenAIDevs account described as now running with better WiFi. The post gives no technical details about what dots is, its capabilities, or its performance figures.

AINarayanan and Kapoor argue that existential-risk framing of AI safety is polarizing and may crowd out work on cyber, bio, and accumulative risks. They propose a big-tent movement with broad beliefs, pluralist values, and common policy ground such as transparency and liability.

AIZyphra says its results clarify how state-of-the-art NoPE models encode position and which inductive biases support generalization. It adds that global NoPE could enable models to extrapolate to contexts longer than those seen in training, potentially indefinitely.

AIModels using Kimi Delta Attention show a recency bias, as the mechanism controlling how much earlier information is kept shapes memory. As new information mixes into that memory, nearby words share more information, which gives the model clues about how far apart words are.

AIHamel Husain posted on X that 95% of replies to his post came from bots, asking whether any humans were present. The post contains no further figures or details about the bot accounts.

AIOpenAI CEO Sam Altman says Sign In With ChatGPT and plugin extensions hold more potential than people realize. The post gives no specific features, figures, or timelines.

AIOpenAI CEO Sam Altman said DevDay had great builder energy and that he was amazed people were building whole startups in a single day. The post gives no product names, figures, or announcements.

AIDwarkesh Patel interviews military historian Si Sheppard about how a few hundred Spanish conquistadors defeated the Aztec and Inca empires in the 1500s. The episode covers Cortés's conquest of the Aztecs, Pizarro's conquest of the Inca, and the role of horses, steel, diplomacy, and disease. It is a history episode, with the AI takeover comparison raised only as a framing.

AIAllie K. Miller argues that people can change how they use AI within one weekend by abandoning three habits: prompting, typing, and relying on a computer screen. The post offers no specific tools, products, or steps beyond these three directives.

AIThe Sequence argues that AI compute could become a commodity that requires a futures market, because unused GPU-hours cannot be stored and suppliers and buyers face forward-price risk. The piece says realizing this requires defining what is traded, measuring its quality, and building contracts around its risks, drawing on commodity market history.

AIRobert Englander argues that natural language interfaces built on top of deterministic software may prove more valuable than fully autonomous AI agents. He contends that large language models excel at interpreting human intent, while systems of record must still provide the reliability, consistency, and accountability that probabilistic models lack.

AIEthan Mollick says he was wrong to think coordinating AI agents would require careful human-designed management structures. He points to personal agents like dots and Muse, and to a swarm of thousands of OpenAI agents that solved a Navier-Stokes problem in 88 hours with thin coordination. He argues many management problems stem from human limits, which agents lack, so people should mainly guide direction while agents handle organizing.

AIStratechery has published an interview with journalist Jason Del Rey comparing Amazon and Meta, extending the long-running retail rivalry between Amazon and Walmart. The provided text contains only the interview introduction and Stratechery subscription material, so no further details on Muse or specific findings are available.

AIIn a YouTube video, PewDiePie reportedly describes agentic training using GRPO, though the post says he does not name a specific tool. The author notes he attempted to distill Sol, was banned several times, and built a website for donated traces that received none, suggesting he could have used the Hugging Face Hub instead.

AIJason Liu (@jxnlco) asks on X whether "dots" should be a separate app. The post gives no further detail about what dots is or what the proposed app would do.

AIThe author gave the first half of a children's saying, "if you're serious, it's interesting," to qwen3-32b-instruct. The model's top predictions were "success" and "gain," while "interesting" did not rank in its top twenty, illustrating how LLMs work by predicting the next word.

AIThe author, @indigox, shares three linked strategies for business owners: automating company work with an Agent Loop, building personal presence and influence, and investing earnings in next-generation tech companies, mainly US stocks. The post presents these as a complete future plan, with no supporting details or figures.

AISherwin Wu says it has never been a better time to build a ChatGPT plugin. The post, quoting Greg Isenberg, argues that ChatGPT now recommends plugins mid-conversation, so early builders can gain distribution.

AIHamel Husain posted a short thank-you emoji reply to Lance Martin's update on an evaluation skill for Claude. Martin says the latest skill now instructs Claude to build a viewer for eval examples, but it does not walk users through the data first, which he agrees could help them prioritize which evals to write.