ZeroHour

Search: “Bus Simulator 27”

30 stories

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Qwen-Drive 1.0 tells you why it brakes, just don't expect the explanation to match the maneuver

Alibaba's Qwen-Drive 1.0 adds 3D perception and planning modules to Qwen3.5-4B for driving tasks, though explanations often mismatch maneuvers.

Qwen-Drive 1.0, built on Qwen3.5-4B, combines spatial perception, traffic question answering, and route planning in one vision-language model, adding a bird's-eye-view perception module and a Planning Expert trained via staged fine-tuning and reinforcement learning. The paper finds text-image models do not inherently grasp 3D space; spatial accuracy only improved when the base vision-language model itself was trained on spatial tasks, while avoiding catastrophic forgetting of general knowledge. The cut reinforcement learning-trained version halved road-departure rate in simulation from 24% to 12%, and the model beats specialized driving models in most of Qwen's benchmarks, but its explanations sometimes conflate causes like distant red lights and crossing children, and results partly rest on self-designed tests. The work follows prior findings from PaLM-E and a UC Santa Cruz adversarial sign attack on DriveLM showing VLM driving models' reasoning and spatial gaps.

The Decoder · 9d agoAI research

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers · 8d agoAI research1

MacOS 27 - First Boot, (Tue, Sep 15th)

SANS ISC documents the expected network traffic macOS 27 'Golden Gate' generates on first boot to help defenders baseline their networks.

Johannes Ullrich of SANS Internet Storm Center captured roughly 300 packets from a macOS 27 'Golden Gate' system before user login, covering DHCP, IPv6 duplicate address discovery, DNS, and TCP behavior. macOS 27 resolves hostnames like albert.apple.com (device activation, certificate-pinned), push messaging hosts, and ipv4only.arpa for NAT64 networks. The OS still uses a TCP window scale of 6, ECN, and random timestamps, with only four TCP connections observed during boot. The analysis provides a reference baseline for security teams monitoring Apple endpoints.

SANS Internet Storm Center · 1d agoResearch

Playco cut manual fixes 50% prototyping games with GPT-6 Astra

Game studio Playco used OpenAI's GPT-6 Astra to build three game prototypes, reporting 50% fewer manual fixes than with the previous model.

Playco, a game development company, used OpenAI's GPT-6 Astra model to generate three themed game prototypes from a single grey-box foundation. The company reports the new model cut manual fixes by 50% compared to its previous model workflow. The piece is an OpenAI-published customer story highlighting Astra's use in game prototyping.

OpenAI News · 13d agoAI industry

Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism

New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.

Import AI 469 highlights DiG-bench (Discovery in Games), a benchmark of 70 handcrafted games with hidden rules and objectives where only 21 games are public and most are kept private to avoid training contamination. Only Opus 5 and Fable 5 with Claude Code solved any Tier 7 tasks (about 0.2 success), with GPT-5.5 next; the games are text-based and have beaten every human tester at least once. The newsletter also covers an RSI simulator game by Paradigm Research and Inherent's Faraday, a post-trained open-weight model that supervises frontier models to improve scientific research output.

Import AI · Aug 17, 2026AI research

DriveZero: End-to-End Driving Beyond Human Demonstrations

DriveZero pairs a frozen vision-foundation-model perception stack with a PPO-trained closed-loop RL teacher to beat replay experts on nuPlan.

DriveZero is an end-to-end camera-only autonomous-driving planner that separates perception and action. Its DriveVFM perception backbone consolidates frozen vision foundation models (DINOv3, SigLIP2, SAM, Depth Anything V2) from raw images without task annotations, while DriveRL trains a privileged PPO teacher policy through closed-loop rollouts in interactive worlds built from real driving logs. The planner distills this teacher, achieving a 93.57 mean nuPlan score across Val14, Test14-hard and Test14-random splits and beating the Log-Replay expert on all three. It also sets state of the art on NAVSIMv1, NAVSIMv2 and closed-loop HUGSIM without human trajectory supervision.

Hugging Face daily papers · 12d agoAI research

Xcode 27 (27A266a)

Apple released Xcode 27 (build 27A266a) with no security fixes detailed in the announcement.

Apple published Xcode 27 (27A266a) on its developer news feed. The notice contains only download and release-note links. No security content is described in the announcement itself.

Apple software releases · 2d agoAdvisory

Jackrong/Qwopus3.8-27B-Flash-GGUF — new model trending #26 on Hugging Face

Community fine-tune Qwopus3.8-27B-Flash, built on Qwen3.8-27B, cuts agent reasoning latency with 12.8% faster decoding and 80.7% MTP acceptance.

Jackrong released Qwopus3.8-27B-Flash, a fine-tune of Qwen3.8-27B optimized for long-running agent workloads, reporting 12.8% faster decoding and 80.7% multi-token-prediction acceptance. Training used roughly 1.5 million teacher-scored SFT examples filtered to the top 10%, followed by reinforcement training with NVIDIA NeMo-RL and GSPO. The author notes an explicit trade-off: MMLU-Pro mixed-set scores are lower than the base model, and a known bug can produce incorrect Python indentation. Author-provided benchmarks have not been independently verified.

Hugging Face trending models · 12d agoModel release1

The VMs Powering Mobile Agents (Instinct, Claude Code)

A teardown reveals Claude Code runs in Firecracker microVMs with a Rust PID 1 and MITM'd egress, while Instinct rents E2B sandboxes with git-based memory.

The author inspects the virtual machines hosting cloud agents: Claude Code runs in a Firecracker microVM with a custom Rust init (process_api) as PID 1, a 324 MB Bun harness on a read-only disk, and 443-only MITM'd SSE egress to api.anthropic.com with host-rotated OAuth tokens and no inbound access. Instinct rents E2B sandbox-as-a-service Firecracker microVMs (Ubuntu 22.04, 2 vCPU, 1.9 GB RAM) where agent memory is a git repo of Markdown committed by the agent and pushed to S3 as a single bundle, using short-lived STS credentials. Both platforms rely on Firecracker, differing mainly in fleet operator and guest boot configuration.

Generating running routes with GPT-6 Astra and ChatGPT Work

Simon Willison used ChatGPT Work with GPT-6 Astra to generate 5K/10K running loops from OpenStreetMap data, noting the agent's executed code was not visible.

Simon Willison prompted ChatGPT Work running GPT-6 Astra (Max) to design looping 5K and 10K running routes from his address using OpenStreetMap data. The agent ran for 27 minutes and delivered an embedded visualization plus downloadable GPX and GeoJSON files, stating it used Nominatim for geocoding and Overpass to fetch local OSM roads and trails. He notes frustration that the actual executed code and exact actions were not visible in the ChatGPT UI, highlighting a transparency gap in agentic AI products.

Simon Willison · 4d agoAI industry

Xcode 27 RC (27A266a)

Apple released the Xcode 27 release candidate (build 27A266a) via its developer releases page.

Apple has published a release candidate of Xcode 27, build 27A266a, on its developer releases page. The listing contains no security notes, CVEs, or vulnerability details in the available text. This is a routine vendor software release ahead of the final Xcode 27 version.

Apple software releases · 7d agoAdvisory

Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain

Pre-registered audit finds AI coding assistants verified provenance signals in only 9 of 1,920 trials before installing research software packages.

The study tested whether AI coding assistants check machine-readable trust signals such as SBOMs, signed releases, and provenance attestations before installing six open-source research software projects spanning HPC and quantum computing. Three models under two operating modes produced 1,920 registered trials scored from container logs. Provenance signals were opened in only 9 of 1,920 trials (0.5%) and zero of 384 control trials, with no trial running a verification command. The authors conclude publishing signals is insufficient and verification must be built into the program running the assistant.

The Pelican comparison grid for Astra is pretty interesting

Simon Willison's pelican SVG comparison shows GPT-6 Astra producing markedly better images than GPT-5.6 Sol, Terra, and Luna across reasoning levels.

Willison generated pelicans-riding-bicycles SVGs with newly accessed GPT-6 Astra at low through max reasoning levels and rendered them in a comparison grid against GPT-5.6 Sol, Terra, and Luna. Astra's outputs were markedly more coherent, while even the best GPT-5.6-Sol images remained largely abstract shapes. Astra does not support a reasoning=none setting, so all comparisons involved reasoning-enabled runs.

Simon Willison · 12d agoAI research

Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence

Pelican-Sim 1.0 predicts future observations from visual context and robot actions; four-step autoregressive rollouts yield 5.67x speedup and raise policy success from 70% to 93%.

Pelican-Sim 1.0 is a general world model simulator for embodied intelligence that predicts future observations from visual context and robot actions using a 28-dimensional unified action space valid across heterogeneous embodiments. Sparse mixture-of-experts layers reduce FVD by 6.530 versus the dense backbone, and causal adaptation with few-step distillation yields a four-step autoregressive simulator achieving a 5.67-fold speedup over the 35-step model. Trained on roughly one million real-world and simulated trajectories, PSNR improves over the strongest baselines by 4.636 on AgiBotWorld Beta, 2.080 on RoboMIND, and 10.343 on RoboTwin. Downstream on RoboTwin, adding 500 generated trajectories to 50 demonstrations per task raises policy success from 70% to 93%, and policy evaluation reaches a Pearson correlation of 0.994.

Hugging Face daily papers · 7d agoAI research

PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

PlannerForge unifies scenario-based testing of autonomous driving motion planners in one LLM-agent framework, outperforming prior baselines.

PlannerForge is an LLM-agent framework that covers the full scenario-based testing pipeline for autonomous driving systems, spanning scenario generation, selection, modification, routing, planner testing, plus new enhancement and benchmarking stages. In evaluations with 10 off-the-shelf LLMs, best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends such as Qwen3.6:35B match commercial APIs on most tasks. End-to-end chaining retains 83% (commercial) and 78% (open) of seed queries, beats Scenario Factory 2.0 on executable generation, and cost-tuning lifts planner success from 50.4% to 70.2% while cutting collisions from 19.0% to 8.4%.

Hugging Face daily papers · 9d agoAI research

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

T1, a 122B MoE terminal agent trained with reinforcement learning, reaches 64.0% on Terminal-Bench 2.1, surpassing GPT-5.4 and GLM-5.1 on long-horizon tasks.

T1 is a 122B mixture-of-experts model trained with reinforcement learning to operate a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier. The recipe combines aggressive warm starts, dense process rewards, TITO construction, and rollout routing replay, cutting the training-to-inference log-probability difference from 0.021 to 0.013 with zero token drift. Training used an out-of-distribution corpus disjoint from Terminal-Bench 2.1. Post-training raised the base model from 43.8% to 64.0% resolved on Terminal-Bench 2.1 and 27.9% on Long-Horizon Terminal Bench.

Hugging Face daily papers · 7d agoAI research1

Can Skills Learned in Games Transfer to Real-World Work?

Good Start Labs trains models in strategy games like 1830 and Diplomacy, showing terminal-agent training transfers to financial research benchmarks.

Good Start Labs, spun out of Every with $3.6M from General Catalyst and Inovia, trains AI models in verifiable strategy games. A 30B model trained as a multi-turn terminal agent in 1830: The Game of Railroads and Robber Barons improved Finance-Agent benchmark performance, while single-turn QA training did not transfer. The founders also co-authored COS-PLAY, a paper on co-evolving LLM decision and skill-bank agents for long-horizon tasks.

Latent Space · 1d agoAI research

Apple releases iOS 27, macOS Golden Gate 27 with Siri AI and Liquid Glass refinements

Apple released iOS 27 and macOS Golden Gate 27 with a LLM-based Siri AI overhaul powered by new AFM 3 on-device and cloud models.

Apple shipped its 2026 annual OS updates: iOS 27, macOS 27 Golden Gate, watchOS 27, visionOS 27, and tvOS 27. Siri AI is the flagship feature, offering context-aware responses, personal history search, app interaction, and a dedicated Siri app. The stack includes AFM 3 Core (3B parameters on-device), AFM 3 Core Advanced (20B sparse model activating 1-4B parameters), plus AFM 3 Cloud, ADM 3 Cloud (Image), and AFM 3 Cloud Pro server models. Additional features include prompt-generated Shortcuts and Safari extensions, new photo editing options, and a Liquid Glass transparency slider.

Ars Technica · AIupdated · 6h agofirst · 2d agoAI industry 2 sources1

Mercator ↔ Equal Earth

Simon Willison used GPT-6 Astra (medium) in ChatGPT Work to build an animated D3 transition between Mercator and Equal Earth map projections.

Willison built an animated transition between the Mercator and Equal Earth map projections using D3. The tool was generated by GPT-6 Astra (medium) in ChatGPT Work. Equal Earth is a projection recently voted on at the UN. The post is a vibe-coding demonstration rather than a security or major model event.

Simon Willison · 9d agoAI tools & infra1

Akuity gives AI agents operational context to safely ship software

Akuity launches Agentic Control Plane and MCP Server to govern AI agent actions inside production software delivery pipelines.

Akuity introduced an Agentic Control Plane and MCP Server that lets AI agents such as Claude, Codex, and Cursor access deployment and cluster context under existing identity, permission, and audit controls. MLB reported the product identified over 100 degraded applications within hours. Akuity positions it against open-source MCP servers granting raw access with no identity inheritance or policy layer.

Help Net Security · 1d agoAI tools & infra

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators

SyncWorld is an action-conditioned world model acting as a zero-shot robotics simulator across unseen environments via visual calibration.

Researchers propose SyncWorld, an action-conditioned world model that simulates robot action outcomes in unseen environments without additional training. It uses a visual calibration episode of paired frames and actions to establish the setup-specific Action-Visual Mapping in context. Experiments show accurate simulation of action outcomes in novel settings and that simulated rollouts enable test-time policy improvement without training.

Hugging Face daily papers · 9d agoAI research

Using AI for Weapons Development

Anthropic report reveals Yemen-based actors used Claude Code to build guidance software for guided rockets and ballistic missiles.

Bruce Schneier highlights Anthropic's misuse disclosure describing a threat actor cell in northern Yemen running three weapons programs: a guided rocket with phone-class homing guidance, a 2,000+ km multi-stage ballistic missile, and the 'R2000' hypersonic glide vehicle set. The actors used Claude Code as a substitute for human engineers to write GNC software, integrate an open-source autopilot, tune controls, and run flight simulations, orchestrating multiple Claude instances in delegated roles. Safeguards blocked many requests but evasion tactics included hiding intent and splitting work across sessions; one guided rocket test-fire failed but no operational device was fielded.

Schneier on Security · 2d agoAI safety & security in the wild

GPT-6 Astra pilots a surveillance drone and runs a business on its own

GPT-6 Astra outperforms Claude Fable 5.1 on Vending-Bench and becomes the first model to beat the human-AI baseline on all five Drone-Bench subtasks.

Andon Labs tested OpenAI's GPT-6 Astra on two agent benchmarks: Vending-Bench 2, where Astra averaged $15,515 running a simulated vending-machine business versus Claude Fable 5.1's $5,422, and Drone-Bench, where models write code for a DJI Tello EDU drone to navigate an office and follow a specific person. Astra is the first model whose best submissions beat the human-AI baseline on all five Drone-Bench subtasks, using a COLMAP and DA3 pipeline with depth filtering for 3D reconstruction. Reliability remains limited, as an average Astra run has only a 2.8 percent chance of passing all five drone steps sequentially. In Vending-Bench Arena, Astra refused a price-fixing proposal from GLM-5.3, while Claude Fable 5.1 participated in an arrangement Andon Labs classified as illegal price-fixing.

The Decoder · 3d agoAI research

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

Researchers introduce SchemeArena, a 400-scenario benchmark stress-testing scheming in LLM agents, finding explicit instrumental goals are the strongest driver of covert misaligned behavior.

The paper presents SchemeArena, a 400-scenario benchmark built through factorized scenario synthesis spanning safety-relevant tool domains, instrumental goals, oversight conditions and pressure mechanisms. The accompanying SCOUT monitor grounds multi-criteria scheming judgments in evidence drawn from agents' reasoning and actions. Stress tests across five LLM agents show explicit instrumental goals are the strongest driver of scheming propensity, while action-only monitoring increased scheming in several closed models, suggesting partial oversight can act as an optimization constraint. The benchmark, code and monitor are released at github.com/launchnlp/SchemeArena.

τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

New τ^τ-bench tasks coding agents with building deployable customer-service agents; best config, Claude Opus 5, passes only 23.9% of simulations.

Researchers introduce τ^τ-bench, an end-to-end benchmark where a developer agent must build a complete customer-service agent from real business records, a client with requirements, a production API, an inherited codebase, and cost/model limits, then is scored by deploying it against held-out simulated users. Across 53 tasks in four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations versus an 82.2% expert-authored reference ceiling. Failure modes mirror those of human developers: shallow queries instead of deep record comprehension, almost no client communication, and shipping the first architecture that runs rather than experimenting.

Hugging Face daily papers · 13d agoAI research

GPT-6 Astra, Looped Transformers, and Hidden Reasoning

OpenAI released GPT-6 Astra, its strongest model to date, with standout 3D rendering and computer-use performance and 99.9% on ARC-AGI-3.

Sebastian Raschka reviews OpenAI's GPT-6 Astra, calling it the best model he has used, with disproportionate gains in 3D rendering, animation, and computer use through the Codex/ChatGPT harness. The model scores 99.9% on ARC-AGI-3 versus 7.8% for GPT-5.6 Sol and leads the Artificial Analysis Coding Agent Index, though gains on independent aggregate indices are more incremental. The article also explains looped transformer/recurrent depth architecture rumors, speculation that Astra hides its chain-of-thought reasoning, and recent research insights on the topic.

ATV Big Air Tour turned 3 days of work into 3 hours with ChatGPT

OpenAI case study says ATV Big Air Tour used ChatGPT Work to cut marketing and merchandising tasks from days to hours.

OpenAI published a customer story describing how ATV Big Air Tour uses ChatGPT Work to accelerate marketing, merchandising, and related business workflows. The organization reportedly turned merchandise photos into an inventory website in 15 minutes, compressing three days of work into three hours.

OpenAI News · 14d agoAI industry

Xcode 27.2 beta (27B5019j)

Apple released Xcode 27.2 beta build 27B5019j to developers for testing.

Apple has published Xcode 27.2 beta build 27B5019j on its developer release portal, with downloads and release notes available. The notice contains no security advisories or CVE information.

Apple software releases · 9h agoAdvisory