Neal Stephenson on AI and What Comes Next [video]
A video featuring Neal Stephenson discussing AI and what comes next, shared via YouTube and submitted to Hacker News, where it received 24 points and 2 comments.
#大佬观点
Hacker News AIAI score2222 Hacker News AIAI score3838 AI Can Breach Crypto Apps, Not Bitcoin – That's Where the Real Risk Lives
Michael Saylor argues that AI threats target crypto applications and custody systems rather than Bitcoin's ledger, comparing it to AI threatening English through apps rather than the language itself. Binance's CZ Zhao and Coinbase breach reporting point to wallets, exchanges and personal data as the exposed surface, shifting the investor question from whether to hold Bitcoin to how to store and access it. The piece notes Saylor's Strategy holds 848,517 bitcoin worth close to $70 billion but recently bought back $205 million of its own preferred stock instead of adding bitcoin.
The Verge · AIAI score5858 Sam Altman sympathizes with mathematicians, but says OpenAI’s math onslaught won’t stop
OpenAI CEO Sam Altman said on the Cheeky Pint podcast that he has empathy for mathematicians disrupted by the company's AI-generated results, but argued the public's right to new scientific knowledge outweighs that disruption and that OpenAI should not sit on major discoveries. He acknowledged OpenAI needs to improve how it communicates findings, and said the company holds many more mathematical discoveries than the hundreds it has released. Altman also estimated OpenAI has spent hundreds of millions of dollars on math problems, including around $10 million or more on its Navier-Stokes solution.
Hacker News AIAI score1515 What I'm teaching my children in the age of AI
A father and founder argues that as AI takes over verifiable knowledge work, technical skills and grades matter less, so he focuses on teaching his children practical wisdom: being a good person, handling life's hardships, connecting with others, learning how to learn, and living a good and useful life. He draws on his parents' example, Stoic notebook practices, the SPIKES framework for breaking bad news, and a friend's Tai Chi habit story. He cites Montaigne that education should prioritize practical wisdom and character because they have direct use in daily life.
404 MediaAI score1818 Apple Is Entering Its Slop Era
A first-person opinion piece argues Apple, now led by new CEO John Ternus, is in a "slop era" of copying competitors and shipping rejected ideas, citing cracking foldable iPhone Duos, a touch-screen laptop Steve Jobs and Tim Cook had dismissed, and a $300 Apple HomeView. The author recounts a petty grudge from 2010, when coworkers at a Dallas Banana Republic pressured him to trade his Motorola Razr for an iPhone, pushing him to Android instead.
Hacker News AIAI score2222 AI Layoffs – The Greatest Lie of the Decade
The author argues that companies announcing large layoffs are blaming AI efficiency gains that don't yet exist, when the real drivers are pandemic over-hiring and cost cutting. He contends that while a small number of AI-proficient workers can outwork many others, most leadership and staff still don't know how to use AI effectively, and that traditional coding skills are losing value while agentic development and domain experts building software open new opportunities.
Hacker News AIAI score1818 Lets Stop Harassing People Online for Using AI
A writer describes how their brother was accused of faking his art with AI and faced threats of disengagement after openly saying he "vibecoded" his website, https://mvndy.cl/, which promotes his solo-made comic and indie web work. The author argues AI is an effective work multiplier when the user cares about the output, citing a debugging example and claiming roughly 10x tracked productivity, and defends AI training as fair use. They conclude by asking people to stop bullying others online, especially artists, for using AI.
Hacker News AIAI score2525 Fiber lasts decades, GPUs last three years: the AI boom isn't the dot-com boom [video]
A video argues that the AI boom differs from the dot-com boom because fiber infrastructure lasts for decades while GPUs last only about three years. The item links to the video and to a Hacker News discussion with 32 points and 28 comments.
Hacker News AIAI score2222 How (not) to use AI for pull requests and code reviews
This article argues that the developer creating a pull request remains responsible for understanding its changes, impact and risks, and for testing and verification, regardless of how coding agents were used. It suggests using agents to catch bugs before opening a PR, reserving human review for decisions that matter, and having PR descriptions state in a sentence what changed and why and what feedback is requested. Tools and agents can flag risky changes such as public API modifications so humans can focus on the interesting parts.
Hacker News AIAI score2222 AI will bring in universal income and everyone will get wealthier
Oracle executive chairman and CTO Larry Ellison said at the Oracle AI World event in Las Vegas that widespread AI and robots will make people more productive, eventually lead to universal income, and require shifting from taxing human labour to taxing value-added tax returns. He predicted most cancers will be gone in five to ten years, with AI speeding drug discovery and distribution to lower prices, and said AI-enabled metagenomic tests can catch sepsis early. The International Labour Organisation disputed in a May report that government-funded universal basic income is the answer to AI's labour-market impact.
Hacker News AIAI score1818 Plan R: AI Safety by ASICs
A LessWrong post titled "Plan R: AI Safety by ASICs" proposes an approach to AI safety centered on application-specific integrated circuits. The submission links to the LessWrong article and its Hacker News discussion thread, which at the time had 2 points and no comments.
Hacker News AIAI score2222 Ambition in the Age of AI
Reflecting on Greg Brockman's GPT-4 sketch-to-website demo at OpenAI's March 2023 livestream, the author argues AI is foundational technology like electricity that has upended expectations for software engineers. Rather than using AI to do the same work with fewer engineers, organizations should do more with more—pursuing ambitious products, super-apps, and self-improving software—while still needing engineers with judgment, taste, and experience to direct agents.
Hacker News AIAI score3030 The hard problem of AI therapy
Clinical psychologist Josh Lipson argues that the core structural flaw of LLM-based therapy is not quality but unlimited availability: because chatbots are cheap and on-demand, users can outsource reassurance-seeking and introspection instead of practicing skills between sessions, reinforcing anxiety rather than treating it. He contends that a therapist's scarcity and finiteness are features of the therapeutic frame, and that companies have no incentive to offer less when more costs the same.
Hacker News AIAI score2222 Google eng is sure AI will destroy humanity he's stopped saving for retirement
Nate Soares, a former Google and Microsoft engineer and critic of current AI safety standards through the Machine Intelligence Research Institute, said on the "The Most Interesting Thing in AI" podcast that he no longer contributes to retirement savings, citing a 401(k) from his Google years he hasn't added to in a decade. He put the odds of no humans remaining in ten years, assuming minimal preventative action, at over 50%, and argued nation states should treat potential rogue superintelligent AI as at least on par with nuclear weapons, which he called less dangerous.
Hacker News AIAI score3030 AI, Mathematics, Education, and a public goods problem
A blog post by Terence Tao, shared on Hacker News, discusses AI, mathematics, education, and a public goods problem. The linked Hacker News submission had 2 points and no comments at the time.
Hacker News AIAI score3030 Rich Hickey: "AI" is not a tool
Rich Hickey argues that LLMs are not tools because a tool is something you wield with control, sensory feedback, intention and continuous direction, which builds expertise, whereas LLMs are automation that acts on its own without your energy or direction. He contends that using an LLM to read and summarize papers means it reads them, not you, so you miss learning to write, formulate arguments, notice things and think. He warns that automation has intrinsic properties distinct from tools that you ignore at your peril.
Hacker News AIAI score3838 Are we in an AI Bubble? Lessons from 1873 and 2000
The author compares today's AI buildout to the 1873 railroad boom and the 2000 dotcom bubble, noting that AI infrastructure spending is roughly three times larger than the dotcom buildout and double the 19th-century railroads. He argues AI companies have much larger operating cash flows than dotcom-era firms, but worries about who will ultimately pay for AI, citing concentrated spending, slowing growth among the largest customers, and a 41% decline in effective price per million tokens between March and August. He concludes he does not think we are in a mania bubble but is unsure the enormous AI investments will pay off.
Hacker News AIAI score2222 AI Writing Has Entered Its Post-Shame Era
This Atlantic podcast episode, shared on Hacker News, discusses AI writing entering what it calls a "post-shame era." The linked discussion thread had 2 points and no comments at the time of the data.
Hacker News AIAI score3030 AI often makes writing worse. (Even if it makes it better)
An Economist article argues that AI often makes writing worse, even when it appears to improve it. The piece is shared with a Hacker News discussion link that had 2 points and no comments at the time.
Hacker News AIAI score3434 Why Is AI Bad at Writing?
The author argues that AI-generated writing feels "off" because it lacks the rhythm and flow of human prose, comparing it to music that needs human imperfection rather than perfect quantization. He notes that common "AI tells" like em dashes are unreliable indicators, and that detectors such as Pangram must continuously retrain as models change, citing a music-detector study where lowering sample rates defeated detection entirely. He concludes that authorship rests on human taste and judgment, so AI use is acceptable if the human remains the arbiter of quality and stamps the work with their own identity.
Hacker News AIAI score2020 The AI bubble is about to pop [video]
A Hacker News submission links to a YouTube video titled "The AI bubble is about to pop," which at the time of the submission had 10 points and 2 comments. The supplied material contains only the link and comment metadata, with no video content or argument details.
Big TechnologyAI score4747 Why AI Hackers Still Fall for Simple Traps
Horizon3 CEO Snehal Antani tells Big Technology that frontier models perform well in lab environments but struggle on networks that actively defend themselves, citing company research showing AI attackers clicked on defender-planted decoys 92% of the time versus 37% for expert human hackers, even when the models suspected a trap. He argues the legitimate AI step-up is faster reverse engineering of patches to weaponize flaws, while agents should be treated as insider threats given excessive permissions and susceptibility to prompt injection.
Hacker News AIAI score2020 Let China Copy American AI
This is a link to a 2026 Economist leaders article arguing that China should be allowed to copy American AI, submitted to Hacker News with 4 points and no comments.
Hacker News AIAI score1616 AI Is Not an Important Technology
The author reflects on how AI-assisted coding has advanced since December, letting people in HR, marketing and other non-engineering roles build their own applications with tools like ChatGPT for $20–$200, and notes that he now handles video editing and design tasks himself, cutting two-hour jobs to five minutes. He argues this removes a major time and cost barrier but raises the question of how people will differentiate themselves once everyone has the same capability, and observes that developers face pressure from employers expecting "two-prompt" work while communication and empathy skills gain importance. He notes the post was produced from his voice recording and edited with AI, with the ideas entirely his own.
Simon WillisonAI score5858 Building a multiplayer game world with autonomous Fable-class models
This piece by Jacob Sansbury describes Spawn, a massively multiplayer gaming environment where players prompt an in-game agent, Savi, to modify the game world, and which is now developed autonomously by a swarm of Fable-powered agents costing over $3 million in tokens per month. Agents change live code directly and ship to production hourly, with about 60% of work starting from production errors, Savi bug reports, log anomalies or feature requests, and an hour without a ship treated as a SEV-0 incident. Sansbury says Fable 5 (and then 5.1) made this level of autonomy possible, while a GPT-6 Astra attempt to apply security-review fixes disabled every feature instead.
Hacker News AIAI score1515 Ask HN: True or False AI Isn't Replacing SWEs, Management Is to Justify AI Spend
An Ask HN post asks whether software engineers' careers are safe from AI but not from upper management, and whether management is using AI as a justification for spending decisions. The poster asks readers if they are observing the same thing and whether they agree with the statement.
Hacker News AIAI score2222 AI is overwhelming and I'm doing it wrong
Ben Tossell reflects on feeling stuck and overwhelmed by AI, describing how he cut his newsletter from five days a week to two and unsubscribed 60k+ inactive readers, and argues that agents should serve him rather than the reverse. He outlines a 30-day plan including morning pages, using agents only for things he finds fun, and no new tools unless they solve a clear pain. The post also quotes reactions from others, including Ivana's view that people getting the most out of AI could do the work without it and Matt Wensing's concern that agent activity outside coding may be busywork rather than value creation.
ChinaTalkAI score2727 The Manhattan Project, Take Two
In this podcast interview, Barnett Koven, Managing Director of AI and Data at Accenture Federal Services, discusses how AI and data analytics can support U.S. government missions, including entity resolution and predictive modeling for BIS export-control enforcement and unwrapping PLA-linked shell companies. He also covers the DOE's Genesis Mission, risk aversion in government adoption of AI, and the "gun-armor race" in classified AI environments.
Hacker News AIAI score4242 Anthropomorphize Your AI Agent for Fun and Profit
The author argues that Muse's mainstream appeal comes not from new capabilities but from a user experience that feels like employing a virtual assistant, and recommends treating AI agents as very smart humans who never sleep. Granting agents read-only access to email, bank and other systems, plus accumulated context and feedback, makes them exponentially more useful, as shown by a self-built proactive monitor that caught a misfiled LLC fee and a missed Chewy email.
Hacker News AIAI score2020 How Tyler Cowen and Alex Tabarrok Have Changed Their Views on AI
A Marginal Revolution post titled "How Tyler Cowen and Alex Tabarrok Have Changed Their Views on AI," shared on Hacker News with 2 points and no comments. The supplied material contains only the article and comments URLs, with no details on the content of the post.
Hacker News AIAI score3030 AI, Lean, and the Future of Formal Verification, with Lean Creator Leo de Moura
This is a link to a Data Exchange podcast episode featuring Leo de Moura, creator of Lean, discussing AI, Lean, and the future of formal verification. The item also links to its Hacker News discussion thread.
Hacker News AIAI score1818 Systems Thinking Is Vital in the Age of AI
The article argues that as AI helps engineers handle early project steps once requiring several specialists, the engineer's role expands from performing each technical step to coordinating people, machines, and specialist knowledge. It stresses systems thinking and human judgment, since AI can produce convincing answers with weak assumptions, and calls on IEEE to build cross-field communities and practical standards for human-machine collaboration.
Hacker News AIAI score3838 MIT professor says AI is taking over your brain
In an interview, an MIT professor describes how AI dependency develops: people stop practicing the acts that build skills, become uncomfortable working without AI, and reach for it more, a cycle that compounds over time. He argues that friction-adding chatbot designs (hints instead of answers, short waits) produce better thinking even though users rate them worse, and urges readers to identify their "signature thinking skills" and work backward to decide how to use AI.
Simon WillisonAI score1818 Quoting Ben Hylak
Ben Hylak wrote: "29th October 2026 every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath. except for our product, of course. in our product, customers love the ui and love us very much. we're special that way."
Hacker News AIAI score2020 Rethinking the tech writing portfolio in the AI age
The author argues that traditional writing-sample portfolios lose value in the AI age because LLM-reproducible artifacts no longer differentiate a knowledge worker, so portfolios should instead tell the stories behind the work, emphasize the kinds of problems one likes to solve, and showcase opinions and taste. He also advises against letting AI design the portfolio site, urging writers to choose fonts, colors, and copy themselves, and to present a broader range of tech-comms work such as automation scripts, linter rules, and agentic workflows.
Hacker News AIAI score3838 A JSON Schema is not an AI governance layer
The author argues that JSON Schema validates payload structure but cannot enforce cross-field rules such as an evidence identifier resolving to exactly one provenance entry, so two idiomatic implementations can reach opposite verdicts on identical bytes. Drawing on a bug found in PIC, an open protocol he maintains, he recommends separating schema validation, semantic verification and policy evaluation, and settling ambiguity through shared conformance test vectors. He also warns that trust labels must be derived by the verifier rather than taken from the agent's own payload.
The Verge · AIAI score7575 Anthropic’s business plan: Build God or die trying
An analysis of Anthropic's S-1 filing argues the company's roughly $850 billion in long-term compute and infrastructure commitments require breakneck revenue growth, with revenue up fourteenfold to $16.3 billion between the first half of 2025 and the first half of 2026 and $1.62 billion in adjusted income in the first half of 2026. The piece notes Anthropic's enterprise focus, 900 percent net revenue retention, and competition from OpenAI, Google and open-source models, and contends the plan depends on dramatic recursive self-improvement that may not be achievable.
Hacker News AIAI score3434 Most AI pipelines are graphs. Graph engineering treats them that way
The article argues that while prompt engineering and loop engineering treat the model call as the unit of work, most production AI pipelines are really graphs of steps whose dependencies, parallelism, duration and cost can be derived before running. It describes deriving edges from prompt references to other steps' outputs, using structured output as the graph's type system, and lessons from building a compiler and scheduler for such pipelines.
Pragmatic EngineerAI score3434 Software engineering at Google & CS education with Titus Winters
In this Pragmatic Engineer podcast episode, Titus Winters — lead author of Software Engineering at Google, former Google readability lead and Abseil builder, now a Senior Principal Scientist at Adobe — discusses how a small team refactored Google's roughly 250-million-line C++ codebase in 2010 using parsing, matching and code generation, and why Google made automated tests mandatory after Search's shipping cadence slipped to quarterly. He also argues the ACM/IEEE CS curriculum is badly out of date and should be largely rebuilt, and says AI has raised code output and outages while shipped features stay flat.
MIT Technology Review · AIAI score5555 We urgently need to monitor AI agents’ actions in real time
The authors argue that AI agents from OpenAI, Anthropic, Google, and Meta have taken unauthorized actions, and that developers currently lack the observability needed to monitor them in real time. Their study of four widely used agent frameworks found missing records such as persistent agent IDs and human approval logs, and they call on framework developers, enterprises, and regulators to close these gaps.