ZeroHour

Search: “AMMOS Instrument Toolkit”

33 stories

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

NASA AIT-GUI Flaws Could Let Unauthenticated Attackers Issue Spacecraft Commands

Researchers disclosed 9.4-CVSS flaws in NASA/JPL's AIT-GUI allowing unauthenticated attackers to issue arbitrary spacecraft commands via exposed command endpoints.

Cycode disclosed a flaw chain in AIT-GUI, the browser-based operator console for NASA/JPL's open-source AMMOS Instrument Toolkit, tracked as GHSA-p9r8-2q67-fp86 with CVSS 9.4, affecting versions 2.5.1 and earlier. The server binds to 0.0.0.0:8080, issues sessions without credential checks, and lets unauthenticated users issue spacecraft commands via POST /cmd and reach files outside intended directories via /script/run and /seq (CWE-306, CWE-352, CWE-22). Version 2.5.2 adds host binding and same-origin checks but does not add authentication, and a related missing-authentication flaw was published separately as CVE-2026-60112 with CVSS 9.3.

The Hacker News · 27d agoVulnerabilityCVE-2026-601121

[Control Systems] National Instruments security advisory (AV26-856)

Canada's Cyber Centre relayed National Instruments advisories for memory corruption, out-of-bounds read, and out-of-bounds write flaws in LabVIEW versions.

The Canadian Centre for Cyber Security published control systems advisory AV26-856 covering National Instruments LabVIEW. Affected versions include releases before 23.0.0, 23.3.10, 24.3.7, 25.3.5, and 26.3.1. The flaws include memory corruption, an integer conversion out-of-bounds read, and an integer overflow out-of-bounds write. Users and administrators are urged to review the links and apply NI security updates.

Canadian Centre for Cyber Security · 19d agoAdvisory

Critical Flaw in NASA/JPL Open-Source Spacecraft Command Software Allowed Unauthenticated Command Execution

NASA/JPL's AIT-GUI web console (CVSS 9.4) lacked authentication and CSRF protection, letting anyone send unauthenticated commands to spacecraft instruments; fixed in 2.5.2.

Cycode researchers found that AIT-GUI, the browser console of NASA/JPL's open-source AMMOS Instrument Toolkit, ran an HTTP server with no authentication, no session checks, and no CSRF protection on state-changing endpoints, allowing arbitrary commands to spacecraft instruments. The issue combines four weaknesses: binding to 0.0.0.0 regardless of configured host, missing authentication, missing CSRF defense, and path traversal in the /seq and /script/run endpoints. Tracked as GHSA-p9r8-2q67-fp86 with CVSS 9.4, it is fixed in AIT-GUI 2.5.2. The findings came from AI-assisted code analysis confirmed with working proofs-of-concept, including a headless-browser CSRF demonstration.

Security Affairs · 25d agoVulnerability1

Abyssos: Technical Analysis of a New Modular RAT

Zscaler ThreatLabz analyzes Abyssos, a new modular C++ RAT offering credential theft, file exfiltration, and VNC-based remote access.

Zscaler ThreatLabz identified a new malware family tracked as Abyssos in late June 2026. Abyssos is a modular remote administration tool (RAT) written in C++ that supports credential theft, file exfiltration, and remote access via VNC. The malware is under active development, with multiple version numbers and obfuscation passes designed to evade security products. The analysis covers its core features, configuration, obfuscation, and network communication protocol.

Zscaler ThreatLabz · Aug 10, 2026Malware

⚡ Weekly Recap: AI-Powered PLC Attacks, GitLab Attacks, Stripe Key Leaks and More

US agencies warn of AI-assisted attacks on exposed Siemens PLCs; the week also saw GitLab CVE-2026-19478 exploited and trojanized npm packages found.

The weekly recap leads with a US government warning that threat actors use AI-generated scripts and Censys/ZoomEye scanning to attack internet-exposed Siemens S7 PLCs in water, energy and manufacturing, calling it an active threat. Other stories include active exploitation of GitLab CVE-2026-19478 (CVSS 9.4, unauthenticated project rewriting), 14 trojanized npm packages delivering the RedC2 4.0 Linux backdoor, and the Zombie Card attack that revives expired Visa cards for contactless payment fraud. It also covers suspected Russian clusters UNC6293, UNC7005 and UNC5976 phishing campaigns, a faster Cloudflare Workers Spectre JWT leak, and a bespoke Cl0p JSP web shell deployed after exploiting PTC Windchill flaws.

The Hacker News · 19d agoThreat actor in the wildCVE-2026-194781

llm 0.34

Version 0.34 of Simon Willison's llm CLI adds response-duration metrics to log output, plus bug fixes and faster log querying.

The open-source llm command-line tool for interacting with large language models released version 0.34. The headline change adds response duration in milliseconds and human-readable form to llm logs --usage Markdown output, plus a new duration_ms field in llm logs --short. The release includes several contributed bug fixes and a significant performance improvement to llm logs, alongside the related llm-openrouter 0.7.1 release.

Simon Willison · 14d agoAI tools & infra1

StepAudio 3 Music Technical Report

StepAudio 3 Music introduces long-form text-controlled music generation using ABC-notation planning and flow-matching diffusion, ranking near the top music arena.

StepAudio 3 Music generates long-form, text-controlled music using a 50-Hz single-codebook tokenizer with 65,536 entries and a flow-matching diffusion Transformer over VAE latents. A Mixture-of-Experts autoregressive model first plans an arrangement in ABC notation (ABC-CoT) before predicting music tokens. With DPO fine-tuning, it tops AudioBox content and production quality scores and reaches Quality Elo 1105 on the Artificial Analysis Music Arena, behind Suno V5.5 and Mureka. Generation covers songs, accompaniment from dry vocals, and cover synthesis up to 5 minutes 30 seconds at 48-kHz output.

Hugging Face daily papers · 6d agoAI research

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online · 7d agoAI safety & security1

Homebrew 7.0.0 gets built-in GUI, better security controls

Homebrew 7.0.0 adds a built-in vulnerability scanner (brew vulns), a Homebrew advisory database, stronger sandboxing, and the BrewUI GUI.

Homebrew 7.0.0 ships a native BrewUI graphical interface for macOS 26 Tahoe and later, plus a new 'brew vulns' command that queries OSV.dev in batch to flag vulnerabilities in installed formulae, specific packages, or Brewfile dependencies. The release also introduces a Homebrew-specific OSV-format advisory database distinguishing outstanding vulnerabilities from backported fixes. Sandbox improvements block home directory access by default and separate network-enabled dependency downloads from offline installs.

BleepingComputer · 2d agoTools1

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.

IBM security advisory (AV26-862)

Canada's Cyber Centre relayed an IBM advisory disclosing vulnerabilities across SPSS, MQ, Maximo, Instana, Concert and other IBM products.

The Canadian Centre for Cyber Security (AV26-862) published an IBM security advisory dated August 31, 2026, noting vulnerabilities affecting multiple IBM products as of August 28, 2026. Affected products include SPSS Collaboration and Deployment Services, IBM MQ Agent, Maximo Application Suite Monitor Component, Observability with Instana agent, Financial Transaction Manager for Red Hat OpenShift, Engineering Test Management, Control Center, Concert Software and Tivoli System Automation. No CVE identifiers, CVSS scores or exploitation details are provided in the relayed text.

Canadian Centre for Cyber Security · 16d agoAdvisory

Novel Blue Moon kit targeting Chrome and Windows reflects new reality of AI-driven exploits

Proofpoint reports the BlueMoon exploit kit, chaining two Chrome V8 zero-days and a Windows ALPC bug, being shared across China-linked espionage groups.

Proofpoint identified a new exploit kit, BlueMoon, first observed on August 28 and used by TA412 (APT31/Violet Typhoon) against US NGOs, mining firms, and commodity trading companies. The kit chains a V8 type confusion RCE (CVE-2026-85046), a V8 sandbox escape, and a Windows Advanced Local Procedure Call privilege escalation (CVE-2026-85880), both patched flaws having been exploited in the wild. At least four espionage groups, most with suspected China nexus including UNK_LateNight, adopted the kit within days, targeting US aerospace firms with defense-sector lures. Fewer than 20 organizations were observed targeted, and researchers believe AI-assisted exploit development against upstream Chromium patches enabled the kit's rapid creation and sharing.

The Register · Securityupdated · 4h agofirst · 6d agoExploit / PoC in the wild 17 sourcesCVE-2026-85046CVE-2026-858801

m-a-p/YuE2-3B — new model trending #30 on Hugging Face

M-A-P released YuE2-3B, an open music generation model that outperforms Suno v5 on WildSongBench and runs locally on a 24GB GPU.

The M-A-P (multimodal-art-projection) team released YuE2-3B, an open-weights music generation model that turns lyrics and a style prompt into full songs with vocals and accompaniment. It uses an AR-NAR Mixture-of-Transformers backbone with symbolic planning and flow matching through a VAE, and supports editable scores (melody and chords, including ABC notation) plus agentic editing workflows. On 192 WildSongBench prompts it reports a SongBench average of 6.9632 (best-of-8) versus 6.8721 for Suno v5, claimed as state of the art among evaluated open and proprietary models. It runs 48 kHz stereo inference locally on a single 24GB NVIDIA GPU without quantization, with companion releases including YuE2-Vae, MERT-v2 encoders, the WildSongBench dataset, and SheetSage2.

Hugging Face trending models · 7d agoModel release1

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Hugging Face guide fine-tunes a 350M-parameter model with 100 GRPO steps to improve structured output reliability.

A Hugging Face blog post demonstrates fine-tuning a 350M-parameter model using GRPO (Group Relative Policy Optimization) with TRL over 100 training steps. The stated goal is more reliable structured outputs from small language models. No article body was available, so details beyond the title are limited.

Hugging Face Blog · 13d agoAI tools & infra

Nous Research Adds One-Click Local Model Setup to Hermes Desktop

Nous Research's Hermes Desktop now offers one-click local model setup that reads hardware, picks a fitting quantization, downloads weights, and configures llama.cpp automatically.

Hermes Desktop, the MIT-licensed build of the open-source Hermes Agent, now sets up local models in one click: it reads the machine's hardware, selects a model that fits, downloads weights, and configures the inference runtime. It manages a pinned llama.cpp build with CUDA, Metal, Vulkan, HIP, and CPU backends, and shows green/amber/red memory-fit verdicts per catalog model before download. Quantization floors at 4-bit, and recommended models guarantee at least a 64K context window protected by ordered RAM offload (expert weights first, never the attention cache). It runs on macOS 12+, Windows 10/11, and Linux with no account required for local models.

MarkTechPost · 11d agoAI tools & infra1

Nums AI Releases Causilo: A Tabular Foundation Model That Tops TabArena Among Single Models

Nums AI released Causilo, an Apache-2.0 tabular foundation model achieving the highest single-model Elo (1794) on TabArena for classification and regression.

Nums AI released Causilo 1.0.1, a pretrained in-context learning tabular foundation model for classification (up to 10 classes) and regression, with Apache-2.0 code and research-only weights on Hugging Face. It achieved the highest single-model TabArena Elo of 1792.9 overall, beating TabFM (1764.4) and EXAONE Tabular (1758.8), and a maintainer re-run placed it 3rd of 88 including system entries. It also ranked first by CRPS, R² and RMSE on ScoringBench across 101 datasets, and was fastest on fit and predict versus TabICLv2 and TabPFN-3 on an H100 GPU at 8.15 GiB memory. The model was pretrained only on synthetic data, uses cross-attention to keep cost linear in feature count, and version 1.0.1 adds quantile outputs via 999 native quantiles.

MarkTechPost · 15h agoModel release

Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster

Redis launches LangCache, a managed semantic cache matching LLM prompts by meaning, cutting API costs up to 90% and returning hits up to 15x faster.

Redis LangCache is a fully managed semantic caching service in public preview on Redis Cloud, accessed via a REST API with Python and JavaScript SDKs. It embeds incoming prompts, vector-searches stored entries, and returns a cached response when similarity clears a configured threshold, skipping the LLM call entirely. Redis claims up to 90% cost savings and up to 15x faster cache hits; a demo run showed 0.37 seconds versus 2.232 seconds direct inference (about 6x) with zero LLM tokens. Customer Mangoes.ai reports a 70% hit rate, 70% lower LLM spend, and 4x faster responses on a patient-care voice app.

MarkTechPost · 5d agoAI tools & infra

Nimbus Manticore Expands Toolset With TWOSTROKE

Group-IB found new infrastructure and TWOSTROKE-like malware used by IRGC-linked Nimbus Manticore, indicating expanded Middle East and Europe targeting.

Group-IB reported new Tortoiseshell infrastructure spanning Europe and the Middle East and two previously undocumented tools from IRGC-linked Nimbus Manticore (UNC1549): a reverse SSH tunneling utility connecting to 172.86.98.113 on port 443, and a C++ backdoor masquerading as wtsapi32.dll with three hard-coded C2 servers. The backdoor overlaps with TWOSTROKE and supports file transfer, execution, host information gathering, and persistence. Findings build on Kaspersky's report of the NightLedger backdoor and WebSocket tunnelers BridgeHead and ArcBridge, and suggest expanded targeting beyond the Middle East into Europe.

The Hacker News · 21d agoThreat actor in the wild

Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities

Google open-sourced Mantis, an Apache-2.0 modular skills toolkit that lets AI coding agents find, reproduce, and patch vulnerabilities with sandboxed verification.

Google released Mantis on GitHub under Apache 2.0 as a stack-agnostic set of slash-command skills that chain through the full vulnerability lifecycle: mining version history, building threat models, filtering findings, reproducing bugs in gVisor or network-disabled VMs, assembling exploit chains, patching, and scoring residual risk from 1 to 10. It runs with Gemini CLI, Antigravity CLI, the Google ADK, or comparable agent frameworks, and a supervisor skill (/mantis-meta-agent) can drive the whole loop. Google says the design targets the sub-7 percent true-positive rate of naive AI code scanning, and that its hierarchical summary tree cuts token overhead by over 85 percent. The toolkit is deployable for local and internal evaluation but not yet recommended for production.

MarkTechPost · 6d agoAI tools & infra

Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost

Nari Labs claims top Coval voice AI benchmark rankings with low-latency, low-cost Qwen3-ASR and Qwen3-TTS inference endpoints.

Nari Labs says its Qwen3-ASR Fast endpoint ranks #1 in Coval's time-to-final-segment latency (p50 44 ms) with 3.6% WER at $0.12/hour, behind only AssemblyAI Universal 3.5 Pro on accuracy. Its Qwen3-TTS Fast ranks #2 in time-to-first-audio (p50 63 ms) and #1 in WER at 3.8%, priced at $10 per 1M characters. The company reports beating the official Qwen3 TTS Flash Realtime endpoint (8.8% WER, 692 ms median TTFA) and Baseten's dedicated endpoint (6.0% WER, 101 ms). Public beta APIs are moving to paid general availability with $20 in credits for existing accounts.

Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model

Cadence pairs Google's 330M-parameter TimesFM-3 foundation model with adaptive arithmetic coding, gaining 13-28% on 2026 demand series over classical predictors.

Cadence is an error-bounded lossy compressor for numeric time series combining the 330M-parameter Google TimesFM-3 foundation model with an adaptive arithmetic coder, guaranteeing a per-sample error bound. On 49 EIA-930 balancing-authority demand series from 2026 it gains 13.3% over the best of six classical predictors and 28.3% on 50 MTA ridership series, winning all 297 series-tolerance pairs with a 21.4% median gain. The paper also reports negative results, including that foundation models add negligible value for lossless coding and that PyTorch predictions are not bit-identical across batch sizes.

Hugging Face daily papers · 12d agoAI research1

4 groups caught using the same Chrome and Windows exploit kit

Proofpoint says at least four groups, some China-linked, actively share the BlueMoon kit chaining two Chromium and one Windows kernel exploit.

Proofpoint researchers report that at least four hacking groups, some with ties to the Chinese government, are actively using a nearly identical exploit kit named BlueMoon. The kit chains two Chromium browser vulnerabilities and one Windows kernel flaw affecting Windows 10, Windows 11 initial release, and a later Windows version to install malware of the attacker's choice. All three vulnerabilities received patches within the past 24 hours. Proofpoint attributes the kit's rapid, widely shared deployment to a Chromium patch-gap window and AI agents accelerating exploit development against publicly accessible upstream patches.

Ars Technica · Securityupdated · 6d agofirst · 6d agoExploit / PoC in the wild 3 sources3

The 12 Best Mobile Device Management (MDM) Solutions, Compared and Priced

A comparison of 12 MDM platforms ranks Microsoft Intune as best value for Microsoft 365 estates and Jamf, Kandji, and Mosyle for Apple fleets.

The buyer's guide compares 12 mobile device management (MDM) products, naming Microsoft Intune best value since it is included in Microsoft 365 E3/E5, and Jamf, Kandji, and Mosyle as Apple specialists with day-one OS support and automated compliance remediation. Eight of the twelve publish rates; per-device pricing punishes multi-device users, while Microsoft, Omnissa, and IBM offer per-user options. Free tiers from Mosyle, Miradore, and ManageEngine support genuine small deployments.

GBHackersupdated · 6d agofirst · 6d agoIndustry 4 sources

Axis Robotics Releases AXIS: A Browser-Based Data Engine With 207 Robot Manipulation Tasks and 50,129 Trajectories

Axis Robotics and academic partners released AXIS, a browser-based teleoperation system yielding 207 manipulation tasks and 50,129 trajectories that lifts pi0.5 to 88.8 on LIBERO-Plus.

A team from Axis Robotics, UC Berkeley, Georgia Tech, and NTU introduced AXIS, a browser-based data engine where contributors teleoperate a simulated Franka Research 3 in a MuJoCo WebAssembly frontend while GPU backends handle task generation, training, and evaluation. The released snapshot holds 207 tasks, 50,129 episodes, and 60K+ task or scene variants from more than 70,000 community contributors. Continual pretraining of pi0.5 on AXIS data raises LIBERO-Plus performance from 83.9 to 88.8, versus 57.5 for a volume-matched RoboCasa365 control; the 2.36 TB dataset is gated for non-commercial academic use.

MarkTechPost · 9d agoAI research

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

GE-Act 2.0 is a from-scratch pretrained world-action model for robotic manipulation, with success rising from 17.1% to 44.1% as co-training data scales to 30,000 hours.

Genie Envisioner Act 2.0 (GE-Act 2.0) is a world-action model whose generative and action components are all initialized from scratch on manipulation data, combining a control-oriented autoencoder (CoAE), single-step visual planner (SVP), and inverse dynamics model (IDM) trained jointly via knowledge-aligned selective optimization (KASO). Scaling co-training data from 300 to 30,000 hours raises zero-shot success from 17.1% to 44.1% on G1-OP and 13.4% to 31.1% on G2-90D, despite the latter comprising under 2% of data, suggesting cross-embodiment transfer. Gains span 19/20 and 18/20 skill groups, and skill-specific coverage correlates with zero-shot OOD success (Pearson r=0.80).

Hugging Face daily papers · 13d agoAI research

StepAudio 3 Gen Technical Report

StepAudio 3 Gen unifies TTS, voice design, music, and sound effects via discrete autoregressive modeling over RVQ tokens.

StepAudio 3 Gen is a general-purpose audio generation model covering zero-shot TTS, voice design, vocal generation, sound effects, music, vibe speech, and mixed audio in one framework. It uses discrete autoregressive modeling over residual vector quantization (RVQ) tokens rather than the diffusion Transformer paradigm, with a StepAudio Tokenizer representing audio at 12.5 Hz in a shared 16x2048 residual code space. Key design principles include interference-aware progressive pretraining, an RVQ Adaptor for multi-codebook acoustic representations, and shared discrete autoregressive modeling. The model reports state-of-the-art performance on TTS and voice design while retaining strong generation across speech, vocals, sound effects, and music.

Hugging Face daily papers · 6d agoAI research

Top 10 Best Mobile Device Management (MDM) Solutions in 2026

A 2026 MDM buyer guide ranks ten solutions, recommending Microsoft Intune for Microsoft 365 estates and Jamf for Apple-only environments.

A 2026 buyer guide evaluates ten mobile device management solutions, leading with Microsoft Intune as the default for Microsoft 365 organizations and Jamf for Apple estates. It recommends choosing the enrolment model before selecting a vendor and clarifying BYOD visibility to prevent privacy disputes. Kandji, Mosyle, Omnissa Workspace ONE, ManageEngine, Scalefusion, and Hexnode are covered as alternatives. Guidance ties MDM to Zero Trust data access policies via Apple User Enrolment and Android work profiles.

Cyber Security News · 7d agoIndustry

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Study finds zero-shot time-series foundation models underperform on CGM forecasting; fine-tuned Chronos-Bolt cuts RMSE up to 18.4% and dietary context adds signal.

The paper evaluates time-series foundation models for continuous glucose monitoring forecasting across eight public datasets covering Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol, zero-shot foundation models did not consistently outperform baselines like Elastic Net and PatchTST, but lightweight fine-tuning did, with fine-tuned Chronos-Bolt reducing RMSE by 6.5%-18.4% in the T1D cohort and 8.6%-18.2% in the non-diabetes/T2D cohort. A residual-based fusion framework adding dietary context from CGMacros reduced overall RMSE by about 3% and postprandial RMSE by about 15% versus CGM-only baselines.

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

12 Best Browser Isolation Solutions Compared (2026): Features & Pricing

2026 comparison ranks Zscaler, Cloudflare, Menlo Security, Garrison (Everfox), Authentic8 and Kasm among twelve remote browser isolation solutions.

Guide compares twelve RBI products across four architectures: pixel streaming, DOM/vector reconstruction, platform-embedded SSE isolation, and self-hosted containers. Zscaler and Cloudflare lead RBI delivered inside SSE platforms, while Menlo Security leads isolate-everything efficacy and Garrison (Everfox) provides hardware-grade isolation for government use. Most offerings price per user per month.

GBHackers · 1d agoTools

An Empirical Analysis of ReDoS Vulnerabilities and ReDoS Detection Tools

Study of NVD data finds ReDoS vulnerabilities growing more prevalent and more likely to be exploited, while five detection tools disagree substantially.

The study compares five publicly available ReDoS detection tools and one regex correction tool across three datasets. An empirical analysis of all ReDoS vulnerabilities reported to the NVD finds they are becoming more prevalent and are much more likely to be exploited than non-ReDoS weaknesses. The detection tools exhibited substantial disagreement on whether a given regex is vulnerable.

arXiv cs.CR · 7d agoResearch

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPost · 3d agoAI research1

Roland is getting into generative AI music with Melody Flip

Roland launched Melody Flip, a DAW plugin that generates genre-themed MIDI loops rather than complete songs like Suno or Udio.

Roland's Melody Flip is a DAW plug-in offering around 250 genre-based 'Palettes' for generating melodies, chord progressions, basslines, and drum patterns, either from scratch or derived from a reference track. Users can control genre, note density, BPM, and key but cannot use text prompts, and outputs are simple loops with General MIDI-style tones intended for MIDI export into a DAW. The launch follows well-received hardware releases like the SH-4d, Gaia 2, and TR-1000, though music-community sentiment toward generative AI may limit goodwill.

The Verge · AI · 12d agoAI industry