groundy
articlespage 2 / 7

all articles

feed101–200 of 655 · page 2 / 7
  1. jul 11agentsGame Theory Can Cut Multi-Agent LLM Hallucination, But Only If Payoffs Align
  2. jul 11agentsWebSwarm: Recursive Multi-Agent Search vs Flat Orchestration
  3. jul 11devtoolsVercel Sandbox Hits 32 vCPU: Agent Testing Escapes Laptop Limits
  4. jul 11infraGLM-5.2: vLLM Int4 Drops MTP Without Patches, SGLang FP8/NVFP4 Keeps It
  5. jul 11securityWhat Vercel BotID Catches in SEO Poisoning That WAFs Miss
  6. jul 11securityHow Attribution Graphs Expose Why LLM Refusal Training Misses Jailbreaks
  7. jul 11infraServing DeepSeek on Azure: Compliance Without Owning the GPU Fleet
  8. jul 11cultureWhen AI Generates the Slides, the Talk Stops Being an Effort Signal
  9. jul 10cultureWhen CP-SAT Solvers Set Your Shifts, Labor Laws Become a Soft Constraint
  10. jul 10modelsAnalytic Inference Cuts Bayesian Deep Ensemble Serving Cost, But Leaves Training as the Bottleneck
  11. jul 10cultureWhen AI Counts White Blood Cells, Who Verifies the Result?
  12. jul 10agentsDo Coding Agents Memorize Their Benchmarks? DeepSWE Tests on Unseen Tasks
  13. jul 10modelsTree-of-Thoughts Improves Text-to-Image Prompting by Reasoning Over Hypotheses, Not Pixels
  14. jul 10ossValve Open-Sources Steam Machine E-Ink Screen, Continuing a Hardware Pattern
  15. jul 10devtoolsBun's Rust Rewrite: The Zig Creator's Rebuttal
  16. jul 10modelsFourierQK's spectral Q/K filter cuts TinyShakespeare loss by 79%, but long-context proof is missing
  17. jul 10cultureHow LLMs Catch Illegal Fishing: From Records to Enforcement
  18. jul 10devtoolsClaude Code vs Antigravity 2.0: $20 Terminal Agent vs Free Parallel IDE
  19. jul 10modelsTencent Hunyuan 3's Agent Push Has No Public DeepSeek or Qwen Benchmarks Yet
  20. jul 10infraVercel Makes WAF Mitigated Traffic Free: Recompute Your Edge Cost Model
  21. jul 10culturemmWave Radar Tracks Worker Posture Without Cameras, Opening a Biometric Gray Zone.
  22. jul 10securityCross-Site Prompt Injection: How Web Agents Confine Untrusted Content
  23. jul 10modelsWhen Does Memory, Not Compute, Decide Who Can Profitably Serve LLMs?
  24. jul 10agentsCan a 4B Model Run a Coding Agent? Terminus-4B vs Claude and GPT-4o
  25. jul 10modelsCan We Trust LLM Logic? A Graph-Based Stress Test Finds Three Failure Modes
  26. jul 10cultureDoes AI Belong in Code Review? What 3100 Developers Actually Argue
  27. jul 10infraGLM 5.2 Hosting Compared: Vercel AI Gateway vs Self-Hosted vLLM
  28. jul 10cultureFrontier AI's Economic Exposure Is Jagged: Which Economies Are Most Exposed?
  29. jul 10cultureLLM Burnout Is a Labor-Market Signal, Not Just a Wellness Story
  30. jul 10infraCloudflare DMARC Management GA: What to Configure Before p=reject
  31. jul 09infraClaude Code Permissions vs OS Privilege Isolation: What the Gap Costs
  32. jul 09modelsLongCat-2.0 Hits Claude Opus 4.6 Class on Agents From a 50K-GPU Cluster
  33. jul 09agentsCan You Prove a Governed AI Agent Actually Ran the Action You Authorized?
  34. jul 09ossWhat Pre-Training a 7B Open-Source LLM Actually Costs in Energy and Carbon
  35. jul 09infraLLM Memory Without the RAM: What SSD-Backed Paging Actually Costs
  36. jul 09securityNVD to CNAs: Why Distributed CVE Assignment Breaks Triage
  37. jul 09securityCVE-to-CWE Mapping With BERT: Multi-Label vs Multi-Class Error Tradeoffs
  38. jul 09agentsAgentTether Repairs LLM Agent Failures with a Runtime Graph
  39. jul 09infraTriton Kernels Pass Tests but Run Slow: The GPU Kernel Eval Gap
  40. jul 09agentsCan Multi-Agent LLM Negotiation Protocols Trust Their Own Samplers?
  41. jul 09devtoolsRunning Gradio Without a Backend: How Gradio-Lite Changes ML Demos
  42. jul 09infraVercel Edge Config: What Global Feature Flags Actually Cost at the Edge
  43. jul 09infraServerless GPU Inference on GCP: What the Cold Starts Actually Cost
  44. jul 09devtoolsCloudflare OAuth for All: What Third-Party SaaS Integration at the Edge Means
  45. jul 09infraVercel In-Function Concurrency: What It Changes for Stateful Node.js
  46. jul 09infraRunning LLMs on AMD GPUs With ROCm: What Actually Works
  47. jul 09agentsWhy Your AI Travel Agent Would Book a Bullfight
  48. jul 08devtoolsCoding Agents Hallucinate Internal APIs: Execution Memory Beats RAG Context
  49. jul 08industryMeta's Layoff Admission Weakens the Case for AI Headcount Cuts
  50. jul 08industryKimi K3 Confirmed for July After K2.7 Lost 11 of 12 Benchmark Cells
  51. jul 08agentsCan Multi-Agent RAG Run Air-Gapped? A Forensics System Shows How
  52. jul 08industryMeituan Open-Sources LongCat-2.0, a 1.6T Model Trained on 50,000 Chinese GPUs
  53. jul 08modelsWhen Do Time Series Foundation Models Pay Off? The Break-Even Threshold
  54. jul 08agentsCan You Prove an Agentic Trading Pipeline Has No Look-Ahead Bias?
  55. jul 08agentsHow Far Ahead Can a Coding Agent Plan? The Horizon Bottleneck
  56. jul 08infraCloudflare Meerkat: What Globally Distributed Consensus Costs at the Edge
  57. jul 08infraVercel CDN Now Honors External Origin Cache-Control: Audit Your Headers
  58. jul 08industryPrompt Refinement vs Reflective Dialogue: Which Builds Better AI Coders?
  59. jul 08infraAI Found Real Bugs in Cloudflare's Circl Crypto Library
  60. jul 08infraPruning RAG Context: What to Cut Before the LLM Sees It
  61. jul 08policyCan US Export Controls Contain AI Built Without American Chips?
  62. jul 08devtoolsThe Vercel-Supabase Pairing Exposes the Distribution Tax Backend Vendors Pay
  63. jul 08policyEntropy Regularization Buys RL Robustness That Certification Can't Credit
  64. jul 08policyFusion's ML Disruption Predictors Have No Shared Validation Standard
  65. jul 08devtoolsVercel Flags Segments Reach the CLI: Feature Flags as Code, Not Dashboard Clicks
  66. jul 08industryOpenAI's Latest Funding Round Bets Investors Will Wait for a 2027 IPO
  67. jul 08infraCloudflare's x402 Gateway: What Per-Request API Billing Actually Needs
  68. jul 08policyAI-Generated CSAM Risks Expose Filter-First Safety Gaps
  69. jul 08policyTreating AI Governance as Code Moves Compliance Into the Build Pipeline
  70. jul 08policyGitHub Issues Are Now Where GDPR and CCPA Compliance Gets Decided
  71. jul 08devtoolsComposed CLI Commands Bypass Coding Agent Approval Gates, MOSAIC Shows
  72. jul 08industryTencent Hunyuan Hy3: Does Smaller Actually Beat Flagship Open Weights
  73. jul 08policyDeepSeek V4 Peak-Load Pricing Breaks Continuous Access for API Users
  74. jul 08industrySymbolic Methods Return to AI as Teams Hit Diminishing Returns on Pure Neural Approaches
  75. jul 08policyLARA Shifts Model Safety from Training to Decode-Time Constraints
  76. jul 08ossHomegames After 8 Years: What Solo Open-Source Game Infrastructure Actually Looks Like
  77. jul 07ossSenior SWE-Bench Exposes the Gap Between Code Generation and Software Engineering
  78. jul 07agentsSymbolic Inference Forces Agent Frameworks to Expose Intermediate State
  79. jul 07ossOomwoo Open-Sources a Repairable Robot Vacuum, Splits From Disposables
  80. jul 07industryE-Commerce Sponsored Search Is Becoming an LLM Relevance Problem
  81. jul 07securityIDE Jailbreaks Bypass Chat Guards by Writing Code
  82. jul 07securityJanuscape KVM Escape Breaks x86 VM Isolation
  83. jul 07industryDeepSeek V4 Cache Discounts, Not Peak-Valley Pricing, Shape Cost Decisions
  84. jul 07devtoolsVite+ Beta: MIT-Licensed Now, Paid Tier Later
  85. jul 07policyStochastic Dominance Reveals Where RLHF Safety Filters Hide Tail Risk
  86. jul 07devtoolsVercel's Agentic Infrastructure Push Outpaces Pricing Transparency
  87. jul 07ossBox3D Launches as Open-Source 3D Physics Engine
  88. jul 07modelsVLA Grounder Tests Language Conditioning to Optimize Black-Box Vision-Action Models
  89. jul 07devtoolsCursor iOS Privacy Migration Shows Why Mobile IDEs Can't Be Audited
  90. jul 07modelsBlack-Box LLM Architecture Inference: What API Restrictions Reveal About Hidden Model Structure
  91. jul 07modelsInduceKV Tests Continual Learning for Multimodal LLMs Without Expanding Cache
  92. jul 07cultureUnit Labor Costs Hit Post-War High as Productivity Decouples From Wages
  93. jul 06cultureJune 2026 Labor Force Contraction Tests Structural Detachment Thesis
  94. jul 06devtoolsTab Completion Hides a Vigilance Drop That Copilot Metrics Miss
  95. jul 06cultureJune's Jobs Polarization Reveals AI-Era Skills Repricing
  96. jul 06agentsBOUNDARY_SYNC: Why Multi-Agent Representational Coupling Is the New Coordination Failure Mode
  97. jul 06devtoolsKimi K2.7 Code Lands in GitHub Copilot: What the Integration Excludes
  98. jul 03modelsSonnet 5 vs GPT-5.5: Pricing, Benchmarks, and the Switching Math
  99. jun 30agentsDo Multi-Agent RAG Systems Write Better READMEs Than One Agent?
  100. jun 30securityJailbreaks Hidden in Image Pixels Slip Past Editors' Text Guardrails via an Empty Prompt