iCreatAI News
Back to main site
Skip to content
Nov 6Fri
  1. MarkTechPost71

    Thinking Machines Releases Inkling 2 Small, a 594B MoE With 17B Active

    Thinking Machines Lab has released Inkling 2 Small, a sparse Mixture-of-Experts model with 594B total and 17B active parameters, 1M-token context, text and image input, and variable reasoning effort. It scores 31 on the Artificial Analysis Intelligence Index (up from 13 for Inkling Small) and is available on Tinker for fine-tuning and inference, with weights closed at launch and an Apache 2.0 release planned next week after external safety testing.

  2. Hacker News AI10

    I struggle to believe that AI R&D is ingenious

    This is a shortform quick-take post by Arjun Panickssery, published 30th Dec 2023, in which only the author can create top-level comments. The post carries the title "I struggle to believe that AI R&D is ingenious" and is marked as a 1 min read.

  3. Hacker News AI15

    Show HN: Stitch.ai – New all-in-one workspace with Stitchy the AI assistant

    Stitch.ai launched this week as an all-in-one workspace combining mail, calendar, contacts, tasks, notes, sheets, slides, files, boards and forms, with auto-generated Knots and Tags for labeling work and a "Stitching" feature to link items such as tasks to events or emails to notes. It also introduces Stitchy, an AI assistant that writes emails, schedules events, manages tasks and runs jobs like watching for email replies or sending daily project updates. Signing up provides an @stitch.ai email address with no integrations needed, and the team offers a free 7-day trial while asking the HN community for feedback.

  6. Hacker News AI22

    How accurately did science fiction stories predict AI?

    The author argues that science fiction is descriptive rather than predictive, then scores famous stories against how AI was actually built, what it could do, and how it was deployed. Ted Chiang's "The Lifecycle of Software Objects" ranks first for its account of teaching, maintaining and selling AI, followed by Heinlein's "The Moon Is a Harsh Mistress" and Ken Liu's "50 Things Every AI Working with Humans Should Know." The author found no pre-2017 work that clearly describes the transformer attention mechanism or the sequence from chatbots to agents capable of novel mathematical results.

  7. Hacker News AI75

    Meta Warns Midterm Backlash Threatens AI Data Centers

    Meta executives said Democratic gains in the US midterms will make new data center construction significantly harder, while Goldman Sachs estimated that state and local moratoriums could put roughly 45% of planned US data center capacity at risk. Meta President Dina Powell McCormick said the industry has "not done as good a job as we needed to explain the benefits of these investments," and Goldman noted that "capacity at risk is not capacity cancelled." Hyperscalers rallied after the election while smaller operators such as IREN, Hut 8, Applied Digital and Core Scientific fell between 5.2% and 10% on November 4.

  9. Hacker News AI38

    AI and the Future of the Product Role

    This keynote argues that differing product role definitions stem from two operating models: the project model, which yields feature team product managers and agile product owners focused on delivery, and the product model, which yields empowered team product managers focused on product discovery and outcomes. It contends that agentic AI is automating delivery work, making product owner and feature team roles less relevant while increasing demand for empowered team product managers skilled in discovery, especially for probabilistic AI products. It cites Shreyas Doshi on the distinction between product managers focused on output versus outcome.

  10. Codex Releases10

    rust-v0.169.0-alpha.1

    This GitHub Changelog entry lists the release tag rust-v0.169.0-alpha.1. The supplied material contains only the page's navigation and product menu text, with no release notes or details about the version.

  11. Hacker News AI58

    You Had Me at "Hello": A Chinese‑Language Framework Targeting AI Infrastructure

    Era researchers observed a Chinese-language exploitation framework they named Greeter attacking seven Flowise honeypots across four regions from July to October 2026, using the overrideConfig code injection flaw CVE-2024-58351 to execute commands via chat messages that each read only "hello". The 12-step chain included host reconnaissance, cloud metadata probing, credential discovery, persistence attempts and fileless execution staging, with commands arriving 3.5 seconds apart. A Shodan query found 4,372 internet-exposed Flowise instances, of which 703 of 3,277 version-identifiable hosts had no authentication enabled and 46 appeared to share the vulnerable conditions recreated in the honeypots.

  12. Hacker News AI20

    Open AI Cellular: Open platform for prototyping and testing AI based 6G

    Open AI Cellular (OAIC) describes its mission as providing an open platform for prototyping and testing artificial intelligence-based controllers enabling 6G research. The page announces the OAIC-T v2.0.0 release, which adds RANFusion, a simulator of 5G core network component behaviors and performances, with InfluxDB support, KPI metrics, AI fuzzing using genetic algorithms to generate UE traffic for testing traffic balancing methods, and example test scripts. It also lists past workshops, tutorials and talks, and notes NSF sponsorship under fund numbers 2120442 and 2120411.

  13. Hacker News AI58

    Closed AI models dominate the price-performance frontier

    Village's LLM Atlas finds closed models hold almost every budget on the price-performance frontier, with open-weight models the best buy at only 3% of budgets, the lowest share measured, down from 41% in June. DeepSeek V4 Flash and Zhipu's GLM-5.2 once led large budget bands, but OpenAI's GPT-6 Luna and GPT-6.1 Terra and Anthropic's Claude Haiku 5.5 reclaimed them. The piece attributes the shift to closed labs distilling their own frontier models, releasing full model families, and serving inference at greater scale.

  15. Hacker News AI20

    Scarce Positions of Economic Power Gain from Increasingly Capable AI

    A narrative essay follows Ravi, an IIT Madras graduate doing systems implementation for a multinational outsourcing firm in Bangalore, as AI agents take over his team's work and his division is cut by half amid layoffs and unrest. An accompanying overture argues that the massive capital expenditure on machine intelligence is not a bubble, and that as with Gutenberg's press, oil, the transistor and railroads, the wealth created by a transformative technology accrues not to its inventors but to those who control the means of conduction.

  16. Hacker News AI26

    The Dangerous Illusion of the "Two-Week AI Expert"

    Prof. Gheorghe Ioan Mihalas argues that medical education has been hijacked by "quick fix" AI courses that teach prompt-typing and slide generation while stripping away theoretical foundations, training clinicians to operate opaque technologies without understanding their limits. He contends this produces an "illusion of knowledge" that threatens patient safety, erodes clinical authority as patients arrive with AI-generated demands, and normalizes acceptance of hallucinations and bias. He calls for mandatory, enforceable three-tiered AI education tailored to students, practicing clinicians, and hospital leadership.

  20. Hacker News AI38

    Supermicro Super AI Station Review: The AI Server That Doubles as a Workstation

    Supermicro's Super AI Station (ARS-511GD-NB-LCC) is a DGX Station system built on NVIDIA's Grace Blackwell GB300 platform, pairing a 72-core Grace CPU with 496GB of LPDDR5X and a Blackwell Ultra GPU with 252GB of HBM3E, powered by a 1600W 80 Plus Titanium supply. Its convertible chassis can serve as a desktop tower or be rack-mounted as a 5U system, with dual 400Gbps QSFP112 ports via a ConnectX-8 SuperNIC, 10GbE and BMC networking, and an optional RTX PRO Blackwell 2000 card. The review notes the front I/O is limited to two 5Gbps USB-A ports, there are no USB-C ports, and the liquid-cooled design includes an externally accessible coolant tank.

  21. Platformer40

    The AI backlash needs a plan

    After midterm wins driven partly by voter opposition to data centers and AI accelerationism, Democrats face the challenge of regulating AI, and the author warns they risk repeating social media's regulatory failures by lacking a coherent goal, a backup plan, and cross-group coordination. The piece notes that 40 of 41 data center-related ballot measures went against data centers, and that Congress may have far less time to act on AI than it did on social media.

  23. Hacker News AI48

    Axiom – blocks AI agents from inventing limits your code never defined

    Axiom is a zero-dependency local guardrail that runs as a pre-write hook in Claude Code and Cursor, or as a stdin/stdout filter for other agents, blocking tool calls before writes occur. It uses regex and AST-pattern detection across three components (Noema, Lemma, Manam) to catch hardcoded numeric bounds, auth bypasses, dangerous Bash, secrets, dependency confusion and invented rate limits, with a tri-state TRUE/FALSE/UNKNOWN logic that halts on UNKNOWN. The author states detection is not semantic and can be bypassed with minor obfuscation, positioning it as a first line of defense alongside container isolation, branch protection and secret scanning.

  24. The Verge · AI40

    Airbnb is working on an AI travel agent

    Airbnb said in its Q3 2026 shareholder letter that it plans to roll out an AI agent in the first half of 2027 to help users plan and book travel. The company says the agent will use a custom "AI-native" interface that composes travel-specific elements like maps, photos, comparisons, calendars and itineraries in real time rather than relying on a traditional chatbot. Airbnb also said AI is "the best thing to ever happen to Airbnb" and has changed how it develops products and operates.

  25. The Verge · AI58

    OpenAI is stepping back from NDAs for data center projects

    OpenAI announced new commitments to communities where it is working on data center projects, including that it won't use non-disclosure agreements with public officials, allowing only narrow protections for security information, trade secrets, or proprietary or competitively sensitive information. The commitments also include paying the full cost of electricity it uses and the infrastructure needed to serve it, publishing expected jobs and reporting on hiring, and giving every future "compute campus" it owns and operates a "local compact" reflecting local priorities.

  26. Hacker News AI55

    Paper: Nubank cuts AI agent update cycles from 3 weeks to under 5 days

    The paper presents a hypothesis-driven simulation workflow using the Snowglobe simulator to screen candidate customer-experience agents before deployment, tested on Nubank's Card Delivery agent and its successor Card Management. Across 4 deployed versions, simulated and production version-level binary evaluator scores showed high correlation, and simulation-guided iteration raised transactional net promoter score by 36.69 points in a live A/B test. Screening open-weight configurations in over 16,000 simulated conversations led to a model that increased self-service rate by 8.82 percentage points in a subsequent live A/B test, with no statistically significant change in tNPS.

  27. Artificial Analysis Articles73

    Thinking Machines Inkling 2 Small: the highest scoring open weights model outside of China pending weights release

    Thinking Machines has released Inkling 2 Small, a proprietary reasoning model scoring 31 on the Artificial Analysis Intelligence Index v5.0.1, with Apache 2.0 weights planned for a later, unconfirmed date. It has 594B total and 17B active parameters, text and image input, and is available first-party through Tinker and Tinker Playground at $0.30/$1.00 per 1M input/output tokens. The model gains 18 points over Inkling Small, matches Gemini 3.8 Flash (high), and costs $1.18 per Intelligence Index task.

    Why it matters: The item gives detailed benchmark comparisons and pricing for a newly released model, useful for readers tracking open-weights and reasoning model progress.

  28. Sierra Blog15

    Sierra inducted into JPMorganChase Hall of Innovation

    Sierra announced its induction into JPMorganChase's Hall of Innovation, presented to co-founder and CEO Bret Taylor at J.P. Morgan's 18th annual Technology Innovation Symposium in Palo Alto on October 29. The Hall of Innovation, established in 2011, recognizes privately held technology companies that have made a significant impact at JPMorganChase through innovation, business value, and close collaboration. Chase CIO Gill Haus cited Sierra as a strong collaborator on agentic AI, and Taylor said the company believes the future of customer experiences will be agentic.

  29. MarkTechPost70

    Google Releases Gemini Omni 1.2 Flash: 15-Second AI Video at $0.07 per Second

    Google released Gemini Omni 1.2 Flash, which generates and edits native clips up to 15 seconds (up from 10) and cuts the price 30% to $0.07 per second of 720p video, about $1.05 per 15-second clip. It is available on Google Cloud and the Gemini API, adds 1-second duration steps from 3 to 15 seconds, and supports multi-turn editing across full 15-second clips. Google has not published benchmark scores for version 1.2, and audio references remain allowlist-gated on Google Cloud.

  31. vLLM Blog42

    VeRL-Omni v0.3.0: Async Training and Broader Multimodal Post-Training

    VeRL-Omni v0.3.0 adds asynchronous and decoupled RL execution paths across multimodal workloads, makes the TransferQueue/ReplayBuffer-based V1 trainer the default, and moves the rollout stack to vLLM 0.30.0 and vLLM-Omni 0.30.0. It includes end-to-end recipes for MiniMax H3 audio-video post-training with DiffusionNFT and MiniCPM-o 4.5 AVQA GSPO, where a 4×H800 experiment found separate-async about 9% slower per prompt at natural response lengths but roughly 6.7% faster at 1024 tokens. The release also expands model and algorithm coverage, adds Ascend and AMD ROCm Dockerfiles, and notes upgrade changes including V1 as default, named diffusion media artifacts, and fail-closed attention backends.

  34. Hacker News AI31

    Show HN: Lab Canary – Rating AI labs on whether their staff can speak up

    Lab Canary is a public scorecard that rates what is publicly known about AI labs' staff contracts and speak-up policies against a seven-clause standard: protect real secrets, never gag criticism or whistleblowing. Ratings draw only on public evidence—published policies, public statements and credible reporting—with each rating linked to its source, and "Not public" is shown separately rather than treated as neutral. The site is a single HTML page with public data files on GitHub under the MIT licence, built by an author who discloses having applied for jobs at Anthropic, OpenAI and Google DeepMind.

  35. Codex Releases22

    0.167.0

    Codex 0.167.0 adds an agent command center opened with `codex agents --no-daemon`, unread-result markers in the command center and session picker, cross-backend session switching from the terminal picker, local image attachment previews, and a Google Cloud Vertex AI setup wizard. Bug fixes keep saved chats visible across model provider changes, preserve transcript history when Ctrl+L clears the terminal, and resolve network approval prompts when their requests end. Documentation and chores cover managed network constraints under [permissions.network], DotSlash manifest updates, and reduced jemalloc arena counts for Linux musl builds.

  36. Hacker News AI8

    What the F**k Has AI Done?

    A link to whathasaidone.com was posted to Hacker News, where it received 3 points and 2 comments. The supplied material contains only the article URL and the Hacker News discussion link, with no article text.

  37. Hacker News AI60

    Thursday's $3T tech sell-off, and what it means if you build AI products

    On Thursday 5 November 2026 the Nasdaq Composite fell 5.52% to 24,315.00 and the Philadelphia Semiconductor Index about 11%, after midterm elections gave Democrats both chambers of Congress and voters in ten states rejected most local data-centre measures, which investors read as a cap on the US AI build-out. The selling hit a market already uneasy about AI capital spending outrunning cash flow, distressed-level credit at GPU cloud providers and 10-year Treasury yields near 5%, with more than $3 trillion of Nasdaq market value gone by midday on Fortune's count. The author, who runs product and engineering at an AI company, argues the market repriced the money and concrete behind the build-out while demand evidence did not move, citing AMD's above-expectation guidance and Anthropic's $17 billion third-quarter revenue.

  38. Hacker News AI8

    Post-AI Computer Science

    This page lists the three volumes of "Post-AI Computer Science" on the ThingsPool blog, alongside links to the site's home page and "Shards of Sanity (2026)" post. It contains only navigation and copyright text, with no substantive content from the volumes themselves.

  39. Hacker News AI36

    The Sweet Spot: How One Brain and Thousands of Micro-Adapters Could Save Open AI

    The article argues that open models are bottlenecked by hardware because Mixture of Experts architectures must keep all total parameters in memory even though only a fraction are active per token. It proposes a frozen, quantized base model paired with thousands of 2–5 MB low-rank adapters selected by a two-step hierarchical router, plus Multi-Head Latent Attention to compress the context cache by roughly ninety percent. Because small adapters can be streamed from system RAM or SSD in a millisecond or two, the design lets capable AI run locally on accessible hardware instead of multi-GPU clusters.

  40. Hacker News AI22

    Show HN: Open-world text adventure played through AI agents

    Eremoterra lets you pick any parcel of Earth, hand a prompt to an AI agent such as ChatGPT, Claude or Cursor, and have it describe and build on that patch as if no one had ever lived there. Trying a patch is free for a night; keeping it costs USD 1, a price that rises about 0.7% each time another 0.1% of the planet's 233,280,000 parcels is claimed and doubles every 10%. Patches carry a server-rendered chronicle of events, can be shared by link without an account, and can be populated by a people you define.