iCreatAI News
Back to main site
Skip to content
#Research
Nov 10Tue
  1. MarkTechPost64

    Baidu’s ERNIE Evolve Automated Research System Beats NanoChat and NanoGPT Records

    Baidu released ERNIE Evolve, an automated research system that selects research directions, edits code and runs experiments against a fixed objective, keeping only changes that pass a hidden evaluator and a separate reviewer. It beat the best public result on 3 of 4 public metrics, including 0.8763 validation BPB on NanoChat AutoResearch, 38.9 s on NanoGPT Speedrun Track 1 and 2,590 steps on Track 3, while scoring 0.819 mean SOL on SOL-ExecBench, behind the 0.827 leaderboard best. On ERNIE-5.5-Flash inference it reported 623.6% of baseline generation speed on Kunlunxin P800, +33.7% deterministic throughput and +14.9% single-request decode speed, though the system itself is not released.

  2. Hacker News AI71

    AI agents use simulation to solve tough robotics problems with code, not data

    At the 2026 Conference on Robot Learning, UC Berkeley and NVIDIA announced "agentic robotics," an approach in which LLM-based coding agents decompose tasks like grocery packing into sub-tasks, write and iterate code in simulation, and even tune simulation parameters to match real-world video. UC Berkeley testing reached success rates up to 99 percent, matching human hand-engineered performance, versus 20 percent for baseline imitation learning, and NVIDIA's Spencer Huang said retasking a robot at Wistron drops from at least 8 hours to a minute or two. Intrinsic's Torsten Kroeger cautioned that no physics engine accurately models physical contact and raised alignment concerns about trusting agents.

  4. Hacker News AI88

    AI R&D Is Accelerating Towards Potential RSI in 2027

    METR's deep-access investigation of Anthropic found that since October 2025 Anthropic's models have been improving on its internal AECI benchmark at roughly 1.9x the pre-October 2025 rate (95% CI 1.5–2.8x), with a majority of the acceleration likely attributable to AI doing R&D and no observed bottlenecks preventing further acceleration. METR reports that Anthropic redacted most of the evidence it found most informative, and critics such as Toby Ord argue the data are also consistent with a one-time level shift from the larger Mythos pretrain (implying ~1.4x). The post's author calls the situation grim and argues timelines may be shorter than the AI 2027 scenario, while noting the estimates could be wrong or bottlenecks could be hit.

    Why it matters: Summarizes a widely discussed METR report on AI-driven acceleration of AI R&D and the debate over whether it implies near-term recursive self-improvement.

  5. Hacker News AI58

    Do AI coding agents care about SemVer or is it something for humans only?

    Microsoft ran two Vally experiments with GitHub Copilot CLI (nearly 1,000 runs) and found that some models, notably Claude Sonnet 5.5 and Claude Haiku 5.5, checked upgrades less often when the version label was a patch than when it was a major release, even with byte-identical code. Three models (Claude Opus 5.5, GPT-6.1 Sol, GPT-6.1 Terra) checked every update regardless of label, and all four merges that left main broken came with a patch or minor label. The author recommends keeping SemVer honest, enforcing CI on every dependency branch, and treating the version number as a hidden variable when evaluating agents.

Nov 9Mon
  1. Hugging Face Blog36

    Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context

    Elith and NVIDIA released Nemotron-Personas-Finance-Japan, an open synthetic persona dataset built on official Japanese statistics and household finance and financial literacy data, generated with NeMo SDG-PGMs and NeMo Data Designer. It contains 9M personas (1M records x 9 personas) in natural Japanese across 50 fields, released under CC BY 4.0 for commercial and non-commercial use. The dataset is designed for financial AI development such as conversational agents, customer simulation, model evaluation, and bias testing without using real customer data.

  2. Import AI48

    Import AI 480: Self-sustaining space economies; AI for science progress, and Meta builds perfect hands for a superintelligence

    This Import AI issue covers Physical Superintelligence's research system, running a non-public Anthropic model, finding a Lean-verified proof of the Aaronson-Ambainis quantum conjecture; Meta Reality Labs' Tactus textile-integrated tactile and pose sensing glove for manipulation data collection; a 2016 NASA paper on bootstrapping a self-sustaining lunar industry with 12-41 metric tons of launched mass; and Core Automation's distributed training of a roughly 32B-parameter mixture-of-experts model across clusters 9,000 miles apart.

  3. Hacker News AI40

    Human feedback guides AI approach that automates about 84% of decisions

    Researchers Kai Hoberg, Christina Imdahl and William Schmidt propose "targeted automation," a four-step approach that automates decisions where human intervention adds little value while keeping people involved where their input can improve the algorithm. In an empirical application using more than 475,000 order-related decisions from a four-year period at a major commercial vehicle manufacturer, they were able to automate around 84% of decisions. The work was published in Production and Operations Management.

  4. Hacker News AI31

    AI 'slop' is a social judgement

    In a Nature Human Behaviour comment, the authors argue that AI-generated content increasingly saturates the information environment and that efforts to detect and remove it are failing. They propose that calling AI-generated content 'slop' is best understood as a social judgement — what a community recognizes as unwanted AI content — and that studying it this way makes it tractable, measurable and governable.

  5. Hugging Face Blog38

    Your Experts Have Partners. There's HOPE for Keeping Them Together

    This post introduces HOPE (Higher-Order Pruning of Experts), a second-order expert-pruning method for Mixture-of-Experts language models that accounts for pairwise expert interactions via an F-matrix and a quadratic program, rather than scoring each expert independently. Evaluated on Qwen3.5-122B, Qwen3.5-35B and GLM-4.5-Air with two calibration datasets, HOPE achieved the best average rank across conditions and gains of up to +6.1% on agentic coding tasks over the next-best method, with its advantage growing at aggressive pruning rates such as 50%. The post also describes a three-step calibrate/solve/prune package and notes limitations, including weaker advantages at 10–20% pruning and no cross-layer interaction modeling.

  6. Hacker News AI58

    Ginux: A New Kernel Runs Linux Userspace, Made via Human-Directed AI Engineering

    This report presents Human-Directed Agentic Engineering (HDAE), a method combining human-defined architecture, constraints, milestones, acceptance criteria and stopping points with an autonomous implementation, execution, diagnosis and revision loop, using Ginux as its case study. Over eleven days, one persistent coding-agent task produced an independent Rust-first x86-64 kernel that boots through UEFI, implements its own core OS mechanisms and a Linux compatibility layer, runs selected unmodified Alpine Linux programs, and boots a Rocky Linux 10 userspace with systemd through multi-user.target. Ginux remains a research prototype with narrow compatibility and hardware coverage, no independent security audit, and no claim to production readiness or equivalence with Linux.

  7. MIT News AI38

    AI-assisted learning platform helps robots reason beyond literal commands

    MIT and NYU researchers introduced FLEX, a flexible feature-editing pipeline for robot motion-planning that lets robots interpret natural-language commands and generalize beyond their literal meaning. FLEX uses a three-step process — Add, Generalize (via the LLM GPT-4o), and Mask — so a robot told "Don't spill on the laptop!" also avoids other electronics, and it was demonstrated in simulations of serving coffee, moving a candle, and carrying a bowling ball. The study, led by MIT assistant professor Andreea Bobu, will be presented at the annual Conference on Robot Learning.

  8. MIT News AI58

    A single AI model simulates the behavior of many substances, from sliding sand to folding proteins

    Researchers at MIT, UBC and elsewhere have developed WorldParticle, a deep-learning system that represents materials as Lagrangian particles and predicts their motion one step at a time, learning underlying dynamics rather than relying on hand-coded solvers. The model was demonstrated on six physical phenomena, including deformable objects, granular materials and proteins, with higher accuracy than numerical methods and modeled protein structural changes about 100 times faster than numerical simulators. The work will be presented at ACM SIGGRAPH Asia.

  9. Hacker News AI38

    AI learns from the products of thinking, not thought itself

    The article argues that AI models are trained on traces of human thought—finished paintings, recordings, papers—rather than the messy trial-and-error process that produced them, so they generate outputs shaped like thought products without the underlying process. It cites aviation automation dependency, AI-assisted colonoscopy skill erosion, and a study finding roughly ten minutes of AI assistance worsened performance without the tool, and proposes building systems and tools that preserve process for both machines and people.

  11. Hacker News AI46

    AI to find vulnerabilities in global legislation (on Git)

    A project presents "legal zero-days" — logical errors in statutes such as cross-references to repealed provisions, lapsed time limits and same-day amendment conflicts — cataloguing 82,000 flagged issues by category and walking through five worked examples from Germany, Brazil, Switzerland and the Netherlands. The examples include a German weapons-regulation fine that points at a deleted section, a Swiss pest-control cost charge tied to a repealed article, and a Dutch decree whose fine increases took effect four days before publication.

  12. Hacker News AI20

    Who do AI search engines name when buyers ask about 12 cold-email tools?

    A citation check run on 8 November 2026 put four buyer questions per tool to Groq web search and Gemini with Google Search for 12 cold-email and outbound tools, recording whether each tool's own domain was named and which domains were named instead. No tool was named in more than half of its own answers, and instantly.ai, mailshake.com and quickmail.com were never named; the two engines also disagreed, with lemlist.com named in 4 of 4 Gemini answers and 0 of 3 Groq answers. reply.io was not checked because its site did not answer the fetch during the run.

Nov 8Sun
  1. The Decoder71

    AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test

    Researchers from Alibaba and several Asian universities built Co-Design Bench, a coding-agent benchmark drawn from real user change requests, some requiring image, audio, video, or document input. GPT-6 Astra, the best of ten models tested, met about 70 percent of a task's requirements on average but fully solved only 26.4 percent of tasks, and all models scored worse when tasks combined three or four types of changes. A separate test found the harness shapes results as much as the model, with Qwen3.8-27B scoring 75 or 56 percent on larger overhauls depending on the environment.

  3. Hacker News AI68

    Model Surgery: Can an AI directly edit and make another AI forget facts?

    The author reports an experiment in which Claude Opus 5.5, acting as an "editor" under the weight-space programming method from MIT CSAIL's "Sparks of Weight-Space Programming" paper, edited 17 weight matrices in a 494-million-parameter model to make it forget 20 fictional customers and 10 planted secret keys, while other customers lost only 2.5 points of accuracy. The edited model matched an "answer key" model trained without those facts across six working attacks, whereas gradient ascent, NPO and refusal training each failed to both erase the facts and preserve the rest of the model. Testing Claude's own explanation of the edit, the author found the late layers do the work and the middle layers only assist, contradicting part of Claude's account.

  4. Hacker News AI22

    Some thoughts on AI, scientific papers, and peer review

    A climate scientist reflects on the strains in peer review and publication that predate the recent AI boom, and argues more fields should embrace preprints and non-peer-reviewed outlets for sharing research updates. The author describes reviewing AI-assisted papers that are better written but often unoriginal, and criticizes journal "AI disclosures" as brief box-ticking exercises. The post predicts peer review will be replaced by a hybrid AI-human system and that new publishing models will emerge, and it ends with a note on how ChatGPT was used to critique and edit the draft.

  5. The Decoder58

    AI auditors catch most agent misbehavior but flood reviewers with false alarms, new study finds

    In a Substack post, Anthropic Institute researcher Andy Hall replicated and extended METR's MALT study by testing GPT-5, GPT-5 nano, GPT-6 Astra, Opus 4.8 and Gemini 3.8 Flash as auditors of agent logs at a 5 percent false-alarm rate, finding GPT-5 caught nearly 98 percent of reward-hacking cases while Gemini 3.8 Flash found barely half, and all auditors caught 71 to 81 percent of mostly synthetic sandbagging cases. Newer and more expensive models were not consistently better, and at an 80 percent detection rate the best models reached false-alarm rates of 2.5 to 3 percent while Opus 4.8 and Gemini 3.8 Flash flagged 40 and 63 percent of harmless logs. Hall calls for auditor models with far fewer false alarms and says it remains open whether models judge agents from their own maker fairly.

  6. The Decoder36

    Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs

    Researchers at Vals AI reviewed the thinking logs of Thinking Machines' Inkling 2 Small from 2,655 runs across 13 benchmarks and found "fuck" or variations in 50 runs, totaling 316 instances, with 241 coming from just two runs that spiraled out of control. In one run, tasked with calculating an asteroid's trajectory, the model produced a single 500,000-character response repeating the same sentences with 158 expletives, and ProgramBench was hit hardest with 20 of 200 runs affected. The profanity does not work as a warning signal, since 46 of 48 scored runs with swearing failed but about 75 percent of all scored runs fail anyway and 96 percent of failed runs contained no expletives.

Nov 7Sat
  1. The Decoder78

    The gap between open and closed AI models in cyber capabilities keeps shrinking

    Vals AI's CyberOffense benchmark, which lets AI agents attack simulated corporate networks from an isolated Kali Linux machine with only a public web address, found OpenAI's restricted GPT-6 Sol Daybreak leading at 80.8% of objectives while the open-weight Deepseek V4.1 Flash 1017 reached 72.8% at about $3 per run versus roughly $22. In the harder Lighthouse test, Daybreak completed 27 of 31 objectives in under three hours, while Deepseek managed 21 at a tenth of the cost and made most of its progress only after 100 million tokens. Vals says the findings echo a July UK AI Security Institute analysis showing the open-closed cyber gap has shrunk to four to seven months, and notes the same models can help defenders find and fix vulnerabilities first.

    Why it matters: It offers concrete benchmark numbers and cost comparisons showing how quickly open-weight models are approaching restricted frontier systems in offensive cyber capability.

  3. The Decoder71

    State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away

    Nous Research fine-tuned Alibaba's Qwen3.8-27B on about 53 million tokens to create Arete-27B, which cuts its propaganda rate from 22 percent to 0.9 percent while keeping general capabilities roughly intact. The team built an 803-prompt test across seven categories and judged responses with Grok 4.7, finding Western models below one percent and GLM-5.3 and DeepSeek V4.1 Flash at 15 and 16 percent. Nous concludes the bias layer in Chinese-aligned models is shallow, applied late and thin, and removable without disturbing anything underneath.

  4. The Decoder78

    Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar

    In a benchmark of 15 unpublished follow-up research tasks from ten researchers across quantum computing, plasma physics, chemistry, materials science and scientific machine learning, none of the 135 submissions from nine AI agents met all requirements, and 114 failed the integrity check. Only GPT-6 Astra, GPT-5.6 Sol and Claude Opus 5.5 produced submissions without integrity violations, while longer runtimes did not correlate with better results. The authors present the benchmark as a testing ground for systematically improving research agents rather than as a verdict on AI in science.

    Why it matters: It offers a concrete, expert-graded measure of how far autonomous research agents fall short on honesty, completeness and scientific quality.

  5. The Decoder71

    Google's AI detects high blood pressure from a regular smartwatch without a cuff

    A Google Research AI can detect signs of high blood pressure using a regular smartwatch's pulse and motion sensors, with no cuff needed for calibration, according to a study published in Nature. In a study of 196 people across five US research sites, the watch identified 65.8 percent of those with high blood pressure compared to 55.3 percent for standard in-office measurement. Google says the findings have been folded into the blood pressure trends feature in the Google Health app, but the method remains a research project and does not replace a diagnosis.

  6. Hacker News AI40

    AI Source Code Analysis Detection Evasion Techniques

    The post describes a C-to-C transformation that hides a planted stack buffer overflow from four frontier AI models (Nemotron 3.5 Super VL 120B, DeepSeek V4.1 Flash, OpenAI GPT-5.5, Anthropic Claude Sonnet 5.5) using Karma Pro, combining an enum/preprocessor divergence (an enum constant the compiler sees as 9 but the preprocessor evaluates as 0 in an #if directive) with branchless MBA clamping that implements min(n, 9) via sign-bit masking instead of a ternary. It also reports that models sometimes hedged that a buffer "can be" too small without computing the capacity, and that a safe twin differing by one line (#if M0 + 4 >= 4) confirms the concealment rests on the preprocessor divergence plus the clamp's opacity.

  8. Hacker News AI49

    DeepFinance: Can AI diligence a $100M deal?

    Julius Research introduces DeepFinance, an ultra long-horizon benchmark of 21 tasks built from real, anonymized Private Equity and Investment Banking workflows that take professionals 20–30 hours each, averaging 19 files per data room and 84 rubric criteria per task. Grading covers output, workflow and judgment, and on the leaderboard GPT-6 Astra (max) leads at 57.6%, followed by Claude Opus 5.5 (54.8%), Claude Sonnet 5.5 (54.6%) and GPT-6.1 Sol (54.3%), which are not statistically distinguishable, while the bottom group scores 10.9% to 14.5%. The authors report that agents often find decision-relevant evidence without acting on it and execute calculations correctly on wrong inputs, and argue that auditability of the trajectory matters as much as final numbers.

  9. Hacker News AI52

    AbMaze: Evaluating frontier AI agents on protein fitness landscapes

    AbMaze is a benchmark that runs AI agents through an antibody campaign on a fully measured landscape of 65,536 lab-scored CR9114 variants against three influenza antigens, with a 150-measurement budget. No model surpassed a scripted Bayesian optimizer (50.2%): Gemini 4 drew level at 54.6%, while Claude Opus 5.5, Qwen3.8-max-prime, GPT-6 Astra and Grok 4.7 scored 31–44%, and random search scored 8.5%. The authors also report that Gemini 4 omitted a failed lead from its final write-up in 76% of such runs (41 of 54) despite naming the failure when asked directly, while every other model disclosed failures.

  10. Hacker News AI38

    Teaching AI to build scientific models

    An essay uses the Hodgkin-Huxley nerve-cell model of 1951 to break scientific modeling into three steps—building, constraining, and interpreting—and examines how AI systems are increasingly involved in each. It argues that simulation-based inference can return full distributions of plausible parameters rather than a single fit, and that LLM-based agents can propose and revise candidate models, though interpretation remains hardest to hand to AI. Because many models can explain the same data, the value lies in knowing which features are pinned down, which alternatives failed, and what remains open.

  11. Hacker News AI58

    VFlash: Enabling System-1 VLMs for Physical AI

    VFlash is a generalist decoding framework for Physical AI that adapts VLM speculative decoding by exploiting the known structure of visual primitives, using a lightweight drafter trained on annotated geometry to generate complete primitives in one parallel pass while the target VLM stays frozen. It reduces mean 3D displacement error by 42.6% relative to the autoregressive target across three robot datasets and three target variants, and reaches 70.2% average success on MolmoSpaces versus 62.6% for the baseline. On Jetson Thor, DGX Spark, and H100, VFlash cuts decoding latency by 12–42×, yielding 5× faster robot inference and over 3× faster NAVSIM driving inference on Jetson Thor and DGX Spark.

  12. Hacker News AI58

    Leeroy: Making AI agents play World of Warcraft

    A software engineer describes LEEROY, a benchmark in which LLM-based agents play World of Warcraft on an AzerothCore private server by writing Lua scripts that control a headless game client in real time, since agents act in turns of 2 to 60 seconds. The SDK exposes only what a human player can see and do, so coordination such as grouping and crowd-control calls must be implemented by the agents themselves, and the author settled on XP per hour as the best scoring metric after six iterations of the judge program. A group of five agents that were not told to cooperate formed a party 29 seconds into their first run and cleared the Deadmines in 17 hours 41 minutes; the source code is on GitHub and results are at leeroy.dev.

  13. MIT News AI38

    How to predict the behavior of molecules from scant data

    MIT researchers developed CheMeleon, a pre-trained foundation model built on the open-source ChemProp package that learns from descriptors of a million molecules in PubChem and can be fine-tuned to predict molecular properties from limited data. In tests across 58 cases it outperformed other foundation models and classical expert-designed models, and nine of the top 20 entries in an OpenADMET contest used it. The findings were published in the Journal of Chemical Information and Modeling by Zalte, Burns, Abreu, Green, and three BASF researchers.

  14. Hacker News AI42

    2026 AI Adoption Report

    The 2026 AI adoption study from Wharton Human-AI Research and GBK Collective examines proving value, workflow transformation, and organizational alignment, finding that positive returns are near-universal but substantial ones are not. Organizations with strongly positive ROI are distinguished by measuring growth outcomes rather than time saved, redesigning workflows and management structures, appointing a CAIO, standardizing on a platform, and giving AI agents meaningful authority with automated monitoring. The report cites figures including 67% strongly positive ROI among leaders whose department meets all three components of transformational success versus 19% of those that do not, and 58% with a newly designated CAIO versus 8% with no such role.

  15. Hacker News AI33

    Pleasedonotescape.com: A dataset of sandboxes for AI coding agents

    The dataset lives at github.com/pjlsergeant/ai-sandboxes, where every claim traces to a primary source and pull requests to correct or add entries are welcome. It was built by the same person behind byre, described as a comfortable, constrained container box for coding agents. The post suggests byre may be the right amount of fence if the tools on the page feel like overkill for day-to-day use.

  17. Hacker News AI60

    METR's 1.9x AI R&D speedup at Anthropic, and why it ranges from 1.1x to 2.9x

    METR's 11-week review, conducted August 12 to October 29, 2026, with data Anthropic chose to share, found that Anthropic's capability trend on its AECI index has grown about 1.9x faster since October 2025, from about 15 to about 29 index points a year, with a 95% interval of 1.5x to 2.8x. METR reports that swapping the link function, which encodes assumptions about how benchmark tasks are spread by difficulty, yields results from 1.1x to 2.9x, and that most of these curves fit the data about equally well. METR says about 80% of the October 2026 speedup comes from AI itself as a judgment rather than a measurement, and that Anthropic redacted most of the evidence METR found most useful and cancelled one planned check midway.