ZeroHour

Search: “filigran”

32 stories

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

Attack Chains, Not Just Attack Surfaces: Why Testing Individual Techniques Misses the Point

Filigran introduces Attack Chaining in OpenAEV to continuously simulate multi-stage attack paths, exposing gaps that isolated MITRE ATT&CK technique testing misses.

Filigran announced Attack Chaining, a new scenario type in its OpenAEV platform that links individual techniques into automated, continuously-run multi-stage attack paths, using each step's real output (credentials, tokens, open ports) to branch dynamically toward a final objective. The article cites Filigran's State of Threat Management report, in which 93% of security leaders reported a business-impacting cyberattack in the past 12 months, 88% said AI accelerates attackers, and 84% blamed siloed tools and disconnected testing. The 2025 DGFiP breach is cited as an example where individually survivable weaknesses chained into a major intrusion. The feature includes conditional chaining logic, live attack path mapping, structured findings for identifying chokepoints, and predefined scope and safety guardrails.

The Hacker News · 1d agoTools

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

Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM

French BabyLM entry METRON-FR (125M GPT-2, 92.47M words) shows tokenizer artifacts dominate child-scale zero-shot evaluation; proposes standard diagnostics.

METRON-FR is a 125M-parameter GPT-2 pretrained on 92.47M French words, submitted to the BabyLM 2026 Strict track, scoring 85.97% on the native Quebec-French QFrBLiMP benchmark and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE protocol combining French task-data translation with rank-16 LoRA shows relational tasks gain while world-knowledge tasks regress. Bilingual Lexicon Induction reaches p@1 of 68.84%, 18x above chance, and ablations show single-token zero-shot scoring is dominated by tokenizer and template artifacts at child scale.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs

ModaLens image-swap audit shows report availability cuts MedGemma-27B image sensitivity on MIMIC-CXR from 20.94% to 4.26% answer changes.

ModaLens is a paired image-swap audit measuring how report availability affects image sensitivity in report-conditioned medical VLMs. On MedGemma-27B across 3,199 paired MIMIC-CXR cases from 293 patients (14 questions per case), generated answers changed on 4.26% of image-swap trials with the report versus 20.94% without it, a 16.7-point paired difference (95% CI 15.6-17.7). The original prompt with a lowercase first-token readout gave 4.70% versus 17.07%, and the direction replicated in two further model lineages. Labels derived from reports limit conclusions about visual correctness; code, prompts, and run records are publicly released.

Hugging Face daily papers · 3d agoAI research

Claude Fable 5.1 made me a really nice animated pelican

Anthropic launched Claude Fable 5.1, claiming gains in coding and long-running tasks, with 52.6% on Terminal-Bench-Science 0.1.

Anthropic released Claude Fable 5.1 (alongside Mythos 5.1), positioning it as a new standard for coding, knowledge work, and long-running problem-solving. The model scores 52.6% on Terminal-Bench-Science 0.1, up from 24.7% for Fable 5, versus 29.0% for Opus 5 and 22.4% for GPT-5.6 Sol. Simon Willison's hands-on test found the model produced an impressive animated pelican, though he notes other benchmarks show only slightly improved scores.

Simon Willison · 15d agoModel release1

XHToken/Spark-X2.5-4B-GGUF — new model trending #30 on Hugging Face

XHToken released GGUF weights of Spark-X2.5-4B, a compact model with 1M-token context and 200+ language support, under Apache 2.0.

The Hugging Face repository provides BF16 GGUF conversions of Spark-X2.5-4B, a compact general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. The model uses a hybrid attention architecture, supports a native context length up to 1M tokens, and covers more than 200 languages. Local inference is supported through Ollama and LM Studio via an XHToken llama.cpp fork, with a --think=false flag to disable thinking mode for faster responses. Released under Apache License 2.0; it was trending #30 on Hugging Face at publication.

Hugging Face trending models · 19d agoModel release

Show HN: Pelican-bicycle alternatives (updated for 2026)

Hobbyist benchmark re-runs the pelican-bicycle SVG test on six 2026 frontier models, comparing generation time and API cost per image.

A Show HN post re-runs the classic pelican-bicycle and similar SVG generation tests across six 2026 models: GPT-6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, DeepSeek V4 Pro, Qwen3.8 Max, and Fugu Ultra v2, recording wall-clock time and cost. It also lists 2025 baseline runs with ten models including Claude Sonnet 4.5, GPT-5.2 Pro, and Qwen3-VL-235B-A22B-Thinking. DeepSeek V4 Pro is consistently cheapest ($0.04-$0.10) while Qwen3.8 Max is slowest, taking up to roughly 17 minutes per generation.

Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models

An open methodology toolkit measures whether transformer language models contextualize fixed word forms across domains using bridge forms and layer-wise silhouette analysis.

The manual documents an open toolkit built around 'bridge forms' - identical written words recurring across two or more subject domains with a different sense in each - to test whether transformer language models individuate word occurrences by context beyond the embedding layer. It covers declarative specification of bridge forms, Wikipedia corpus acquisition, occurrence localization, layer-wise representation extraction, domain-pairwise silhouette measurement, and visualization, justifying each choice against failure modes such as sense contamination and subword-tokenization misalignment. It is a methodological and implementation reference and reports no empirical results.

arXiv cs.AI / cs.LG / cs.CL · 12d agoAI research

.blend URL Viewer

Simon Willison demos a .blend URL viewer built with GPT-6 Astra in Codex and ChatGPT Images 2.5 generating Blender models.

Simon Willison used ChatGPT Images 2.5 to generate a Faberge egg concept image themed after the TV show Pluribus, then had Codex running GPT-6 Astra (high) execute a Blender local skill to build a 3D model from it. He published the result as a .blend URL viewer tool and continues experimenting with agentic Blender workflows. The post is a hands-on demo of AI-driven creative tooling rather than a security or release announcement.

Simon Willison · 7d agoAI tools & infra

IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing

Researchers release IndicTriMix benchmarks and fine-tuned MuRIL and XLM-RoBERTa models for token-level language identification in tri-language code-mixed text.

The paper formulates token-level language identification in code-mixed text as a sequence labeling task and fine-tunes MuRIL and XLM-RoBERTa transformer models for Indian languages. It evaluates on Hindi, Gujarati, and Bengali configurations with manually annotated test sets and proposes two code-mixed generation approaches using parallel trilingual sentences. A public benchmark, annotated test sets, and fine-tuned models are released for reproducibility.

arXiv cs.AI / cs.LG / cs.CL · 6d agoAI research1

NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting

Researchers introduce NOAH, a time-aware generative transformer trained on 559 million MIMIC clinical events to forecast multimodal patient trajectories.

NOAH is a task-agnostic, time-aware generative transformer trained on over 559 million clinical events from 431,000 hospital visits by 299,000 patients across the MIMIC dataset family. It uses bidirectional time integration and a variational latent space to model the stochastic evolution of patient states, natively processing medical images, time-series signals, categorical events, and structured or unstructured clinical records. The model supports autoregressive forecasting with optional time control, zero-shot classification, and counterfactual intervention simulation, with strong probing performance across clinical outcomes, 15 ICD chapters, and 29 comorbidities.

Hugging Face daily papers · 9d agoAI research1

Update modules/auxiliary/scanner/http/elasticsearch_tika_xfa_xxe.rb

Rapid7 updated a Metasploit auxiliary scanner module that detects XML external entity injection in Elasticsearch via Apache Tika.

A commit in the Metasploit Framework updated modules/auxiliary/scanner/http/elasticsearch_tika_xfa_xxe.rb, an auxiliary scanner module. The module targets XML external entity (XXE) injection in Elasticsearch through Apache Tika, and was co-authored by jheysel-r7. The terse commit message contains no additional details, CVE references, or exploitation notes.

Metasploit Framework commits · 8d agoTools

NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting

Researchers introduce NOAH, a generative time-aware transformer trained on 559 million MIMIC clinical events to model and forecast patient trajectories.

NOAH is a task-agnostic, time-aware generative transformer designed to represent and forecast the full multimodal patient journey across medical images, time-series signals, categorical events, and clinical text. It was trained on over 559 million clinical events from 431,000 hospital visits covering 299,000 patients in the MIMIC dataset family. The architecture combines bidirectional time integration with a variational latent space to capture continuous patient state evolution and clinical stochasticity. NOAH supports autoregressive forecasting with time control, zero-shot classification, and counterfactual intervention simulation, with evaluations on 15 ICD chapters, 29 comorbidities, and time-to-event prediction.

arXiv cs.AI / cs.LG / cs.CL · 8d agoAI research2

Quoting Rick Brewster

Paint.NET added a clean-room Direct2D rewrite for WINE, largely written by Anthropic's Claude and described as unreviewed 'vibe coded' code.

Rick Brewster says Paint.NET now ships a from-scratch, reverse-engineered Direct2D implementation (PaintDotNet.Windows.Direct2D1.Managed.dll) used under WINE via a /wine flag, since Direct2D was never completed well enough there. He credits the Claude coding assistant with writing most of the code, calling it largely 'vibe coded' and not thoroughly reviewed. Simon Willison shared the quote as an example of shipping AI-assisted systems code in production software.

Simon Willison · 14d agoAI tools & infra1

Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills

Anthropic ships a plugin evals workflow for Claude Code with six grader types, a no-plugin baseline arm, and a CI gate via threshold and cost flags.

Anthropic published a plugin evals workflow for Claude Code, exposed via the "claude plugin eval" command on v2.1.269+. Six grader types exist: regex, tool_used, tool_order, and file_exists are free transcript checks, while llm and baseline invoke a billed judge model. Every case runs with and without the plugin, and the delta (Δ) isolates the plugin's contribution; a Δ near zero with a failing tool_used:Skill grader indicates the skill never triggers. CI gating uses --threshold 0.8, --max-cost-usd, --trust-plugin, and --no-publish flags, with results written to a report.html under evals/results/.

MarkTechPost · 5d agoAI tools & infra2

Claude Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher

Claude Fable 5.1 solved Sir Thomas Urquhart's 370-year-old Cyphral Distich cipher, recovering a hidden royalist prayer for Charles II.

Vals AI reports that Claude Fable 5.1 solved the Cyphral Distich, a 64-number cryptogram from Sir Thomas Urquhart's Logopandecteision unsolved since 1653, in 44 minutes using 176k tokens with no human hints. The key insight was that the cipher's key was the book itself: each number indexes a word in the corresponding Proquiritation, taking the first letter, yielding 'O GOD UPHOLD KING CHARLS THE SECOND AND MAKE HIM THE SUPREME RULER OF THIS LAND'. The model also deciphered the larger Cyphral Octastich (285 numbers) from The Jewel (1652) using page-based word indexing, recovering all but nine letters of a royalist prayer. The puzzle had been listed among Klaus Schmeh's Top 50 unsolved encrypted messages.

Hacker News · AI · 3d agoAI researchHN 63↑ · 6 comments1· 1 read

Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model

Dynin-Robotics omnimodal diffusion vision-language-action model unifies action, dynamics, and goal prediction, reaching 78.4% success on Franka tasks.

Dynin-Robotics builds a shared trajectory model on the Dynin-Omni omnimodal masked-diffusion backbone, representing language, observations, goals, and actions as discrete tokens. One model learns action prediction, action-conditioned next-observation prediction, terminal goal-state prediction, and trajectory-to-instruction reconstruction, enabling test-time scaling through goal prediction and joint refinement. It is continually pretrained on approximately 1.33 million trajectories from 48 Open X-Embodiment datasets and achieves competitive performance on LIBERO and zero-shot LIBERO-Plus plus a 78.4% average success rate across four manipulation conditions on a Franka Research 3 robot. An optimized block-parallel implementation accelerates model-side action decoding by up to 29.2x.

Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation

Rosetta ranks 4th and 5th in AlexandriaX-2026 dialectal Arabic dialogue translation using a LoRA adapter on NileChat-3B, finding limited pretraining benefit.

The Rosetta system for the AlexandriaX-2026 shared task fine-tunes a LoRA adapter on NileChat-3B for context-aware English-to-dialectal Arabic dialogue translation. The adapter was additionally pretrained on MADAR and PADIC dialect corpora for the unconstrained track. It achieved spBLEU 26.10 (4th, constrained) and 25.09 (5th, unconstrained). External dialect pretraining improved only two of thirteen dialects while slightly degrading overall performance, indicating negative transfer.

arXiv cs.AI / cs.LG / cs.CL · 7d agoAI research1

From Hacks to Bioweapons, Claude Misuse Is Now Everywhere

Anthropic reports Claude was misused by Midnight Blizzard, ShinyHunters, disinformation campaigns, and bioweapon attempts; roundup also covers Xinbi takedown.

Anthropic's new report documents eight months of Claude misuse: Russian state-sponsored hackers (Microsoft-named Midnight Blizzard) used it for reconnaissance against Ukrainian and European government networks, stealing data and maintaining access, while ShinyHunters used it across hacking and extortion campaigns, and users attempted bioweapon development. Anthropic says it disrupted the activity. The WIRED roundup also covers the US seizure and sanctioning of Xinbi Guarantee, a Telegram black market with $30 billion-plus in sales mostly laundering pig-butchering scam proceeds, plus DOJ raids on 13 scam compounds in Madagascar and a four-year prison sentence for a Conti ransomware member. Meta faces scrutiny over AI child abuse ads and a class action over photo harvesting for AI training.

WIRED · Securityupdated · 11h agofirst · 4d agoAI safety & security in the wild 18 sources

llm-anthropic 0.28

llm-anthropic 0.28 released with Claude Fable 5.1 support, default reasoning traces and a new ClaudeRefusal exception.

Developer Simon Willison released version 0.28 of the llm-anthropic Python plugin, adding support for Claude Fable 5.1. Reasoning traces are now displayed by default for models that support them, and a new llm_anthropic.ClaudeRefusal exception is raised when Claude returns a refusal.

Simon Willison · 14d agoAI tools & infra2

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

Researchers introduce HoloWorld, a unified text-driven framework generating coherent indoor-outdoor 3D urban worlds, improving average AQS over SOTA by 7.68%.

HoloWorld is a text-driven 3D generation framework that unifies indoor and outdoor urban world generation using a continuously updated cross-scale world context. It autoregressively generates urban exteriors with consistent spatial organization, grounded in 3D building instances and footprints, then produces building-specific interiors with geometry-constrained layouts that inherit exterior appearance. The authors claim it is the first framework to unify indoor and outdoor generation within one coherent 3D urban world, reporting a 7.68% average AQS improvement over prior SOTA and the highest average RDR score.

Hugging Face daily papers · 19d agoAI research

Show HN: LLM Attention Visualization

A developer released a browser-based tool that visualizes which past tokens influence each LLM output token using aggregated, value-weighted attention scores.

A Show HN project presents a React application built on Transformers.js that renders per-token attention influence by aggregating attention weights scaled by value-vector magnitudes across all attention heads and layers. To expose internal tensors, the author instrumented the ONNX computation graph, hosted a modified model on Hugging Face, and pre-generated prompts to avoid long model downloads in the browser. Demos with a 600-million-parameter model show how verbatim copying draws heavily on source tokens and how single outputs blend information from multiple phrases.

Claude's new system prompt really doesn't want to reproduce song lyrics

Anthropic published updated Claude consumer system prompts, including changes steering the model away from reproducing song lyrics, likely over copyright concerns.

Anthropic publishes system prompts for Claude.ai and Claude mobile apps, including historic revisions, and has reorganized them into an index with per-model pages such as the Haiku 4.5 page showing the original October 15, 2025 prompt and an updated January 18, 2026 version. The latest consumer prompt strongly discourages reproducing song lyrics, a behavioral constraint likely tied to copyright considerations. Prompts for Claude Cowork and Claude Code are not included in the published set.

Simon Willison · 14d agoAI safety & security

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

Class action lawsuit accuses Anthropic of overselling Claude subscriptions with deceptive usage multipliers

Class action lawsuit alleges Anthropic's Claude Max plan misrepresents usage multipliers via five-hour and weekly caps.

A class action filed by the same law firm over the summer claims Anthropic's $100 five-times and $200 twenty-times Max plan multipliers apply only within five-hour windows and are capped weekly, delivering less usage than advertised. Anthropic moved to dismiss, saying details were available via hyperlinks during purchase. Plaintiffs argue consumers cannot verify AI service delivery and must rely on honest advertising.

The Decoder · 5d agoAI industry2

LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics

LexFlip releases 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving tokens, exposing weaknesses in embedding-based meaning preservation metrics.

LexFlip provides 373 minimal perturbations of Quebec statutory French that reverse legal force while preserving 0.93 of tokens, creating dissociation items that break monotone token-overlap metric validation. The seven embedding and BERTScore metrics tested register only 0.022-0.039 of their identical-to-unrelated range on these edits, versus 0.670 for bidirectional NLI. Against FrJudge, with a measured human ceiling of r=0.597, a bare length feature outscores every semantic metric tested.

arXiv cs.AI / cs.LG / cs.CL · 12d agoAI research

A new class action lawsuit questions whether Anthropic broke the law by misleading power users

An expanded class-action lawsuit alleges Anthropic deceptively advertised Claude Max subscription usage limits, masking five-hour session and weekly caps.

A re-filed class action led by two former FTC attorneys alleges Anthropic's Claude Max plan, priced at $100 for '5x' and $200 for '20x' Pro usage, misleads buyers because the multipliers apply only within five-hour sessions that are also subject to weekly limits. The complaint was first filed in July, withdrawn, and refiled as an expanded class action; Anthropic's motion to dismiss argued the limits were discoverable via hyperlinks during purchase. Weekly limits were imposed in August despite the Max plan launching in April 2025. Anthropic did not respond to requests for comment.

The Verge · AI · 8d agoAI industry

RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting

RelightFormer is a feed-forward generative transformer for photorealistic single- and multi-view object relighting, trained on a 90K-object dataset.

Researchers introduce RelightFormer, a feed-forward generative transformer adapted from a video foundation model that performs direct image relighting without explicit intrinsic property estimation. The architecture injects target environment maps via a latent illumination module with cross-attention and uses permutation-invariant positional encodings for unordered multi-view inputs. Training relies on the newly constructed Laval Objaverse Dataset (LOD) with 90K objects and 39K unique illuminations, and the model shows state-of-the-art quality with strong zero-shot generalization across single-view, multi-view, and novel-view relighting.

Hugging Face daily papers · 10d agoAI research

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Hugging Face details building and using multi-vector late-interaction embedding models with Sentence Transformers for retrieval workloads.

Hugging Face published a guide on multi-vector, late-interaction embedding models (ColBERT-style) supported through Sentence Transformers. The post covers how practitioners can build and use these models for retrieval and RAG pipelines. It is a developer tooling and technique write-up, not a security advisory.

Hugging Face Blog · Aug 18, 2026AI tools & infra1

Houthis Used Claude Code to Develop Missile Guidance Software: Anthropic

Anthropic's threat report details a Houthi-linked Yemeni cell using parallel Claude Code sessions to build missile guidance software, evading safeguards by fragmenting tasks.

Anthropic's September threat report describes a Yemen-based cell, assessed as highly likely Houthi-linked, that used Claude Code across multiple parallel instances to develop guidance software for a tactical guided rocket, a ballistic missile with over 2,000 km range, and a hypersonic glide vehicle concept called 'R2000'. The operators integrated open-source autopilot software, built six-degree-of-freedom trajectory simulations, and used reinforcement learning to tune flight-control algorithms, ultimately compiling an offline executable. The group test-fired a guided rocket that failed, then used Claude within hours to analyze launch telemetry. Anthropic blocked numerous requests, but operators evaded safeguards by obscuring intent and dividing work across separate conversations before accounts were banned; the case is one of six conventional-weapons cases (three China-linked, two Russia-linked) in a report covering disrupted operations from December 2025 to August 2026.