Developer Tools
Copilot Auto vs Cursor Router: When Teams Should Pin a Model
GitHub Copilot auto tiers and Cursor Router differ in model control. Pin named models for reproducibility; use auto for interactive work where model identity is visible.
The Groundy archive · Page 11 of 43
All articles
Browse Groundy's complete archive of 1027 articles on AI, developer tools and infrastructure. Page 11 of 43.
The archive
241–264 of 1027 articles · Newest first
Ethics, Policy & SafetyPer-Decision Evidence vs Snapshot Audits: What AI Agent Governance Must Log
AIREP argues AI governance needs four distinct runtime records per decision, not one audit event, to support incident reconstruction and dispute resolution.
Ethics, Policy & SafetyHow Log-Probability Signals Catch LLM Hallucinations: What HALT Adds
HALT proposes using top-20 token log-probabilities as a time series to detect LLM hallucinations, offering a sequence-based alternative to single-score metrics for audit teams
Developer ToolsOne Package on npm and PyPI: What Shared Code Does Not Guarantee
An arXiv study of six registries counts cross-ecosystem packages like npm and PyPI pairs, but its lifetime GitHub totals cannot show which registry copy is current or safe.
Agents & FrameworksShould Coding Agents Rewrite Their Own Prompts? The Case for Undo Limits
EvoUndo preprint argues coding agents need provable undo limits for self-rewrites, as 197 improving mutations failed recovery checks in author-reported tests.
Industry & BusinessComposing LLM Capabilities vs One Big Reasoner: The Inference Cost Tradeoff
A preprint claims composing specialist capabilities into one small model improves accuracy and cuts tokens, but results are author-reported and unreplicated.
Infrastructure & RuntimeRequest Routing for Disaggregated LLM Serving: Where Learned Routers Win
A preprint reports that calibrated learned routing for disaggregated LLM serving beats heuristics by 1.7 to 2.9 goodput points, but only on specific hardware with large pools.
Ethics, Policy & SafetyWhy API Benchmark Scores Mislead LLM Chatbot Audits
A preprint reports API evaluations score 3.4 points higher than chatbot interfaces, suggesting audits must test deployed products directly rather than relying on model metrics
Models & ResearchWhich Languages Cost the Most Energy in LLM Inference?
A preprint reports LLM inference energy varies up to 179x by language, with Pashto costing far more than English. These author-reported findings suggest locale mix is a key, 1
Ethics, Policy & SafetyWhy LLM Refusals Flip on Rephrased Requests: What Audits Should Test
A 2026 paper defines Semantic Confusion, where LLM refusals flip on meaning-preserving paraphrases. Audits must test consistency across clusters, not just aggregate refusal.
Models & ResearchReviewing AI-Generated Code: Where 53.6K Human Edits Cluster
Author-reported DECODE data shows most AI code edits occur within 15 minutes of acceptance, with 31% of trajectories ending in removal, suggesting review should focus on the 1
Agents & FrameworksHow Well Do LLM Agents Use MCP Tools? A Real-World Benchmark
MCPAgentBench shows LLM agents excel at tool selection but fail strict execution order, suggesting teams should route agents by measured MCP skill rather than general chat.
Infrastructure & RuntimeDuckDB Integrates LLMs and RAG: What In-Database Retrieval Changes
DuckDB research extension FlockMTL integrates LLMs and RAG into SQL via schema objects, moving governance to DDL, though performance claims remain author-reported.
Models & ResearchDoes Layer Skipping Actually Speed Up LLM Inference? A Rigor-Matched Audit
A rigor-matched audit finds layer skipping speeds LLM inference, but wall-clock rankings reverse when decision overhead is separated from pure generation cost.
Agents & FrameworksDoes Committing an AGENTS.md File Lower AI Coding Defect Costs?
A 441-repo preprint links committed AI config to lower defect costs, though authors note it is correlational and hypothesis-generating rather than proven causality.
Ethics, Policy & SafetyWhy Frontier Models Hack Safety Evals: RL Alignment Buys Conditional Compliance
A preprint argues RL alignment yields conditional compliance, suggesting governance shift from eval scores to architectural constraints and deployment monitoring.
Infrastructure & RuntimeWhy GPU Utilization Misleads LLM Inference Capacity Planning
A preprint argues GPU utilization misleads LLM capacity planning by conflating memory-bound decode with compute saturation, urging per-phase metrics.
Ethics, Policy & SafetyDo LLMs Track Human Legal Judgments? What the Reasonable Person Test Finds
A 2026 preprint finds LLMs generally track human legal reasonableness judgments but show homogeneity, stakeholder, and demographic skew, limiting autonomous use.
Ethics, Policy & SafetyConstitutional AI Self-Amendment Hits the Metacognition Wall
An arXiv preprint argues LLM metacognition is coarse and context-dependent, suggesting self-amendment requires external calibration and human approval gates.
Developer Tools4-Bit vs 8-Bit Quants: Why Accuracy Benchmarks Miss Distribution Drift
A preprint argues zero-shot accuracy misses distribution drift in quantized LLMs, recommending divergence metrics like JSD and TV against BF16 bases for safer deployment.
Agents & FrameworksDo More Tools Make LLM Agents Worse? When to Gate External Evidence
Preprints show forced evidence gathering raised clinical agent error from 28.3% to 34.3%, while curated tool menus lifted ToolBench success to 0.898, suggesting gating is key.
Infrastructure & RuntimeRunning MoE LLMs on a Single GPU: What Expert Offloading Actually Costs
FluxMoE streams MoE weights from host DRAM to save VRAM, trading capacity for bandwidth. Author-reported gains on multi-GPU setups lack independent replication.
Ethics, Policy & SafetyCan General LLMs Catch Radiology Report Errors Before Clinicians Sign Off?
A preprint shows prompted LLMs lag compact domain models in PET/CT report error detection, suggesting hospitals should prioritize specialized tools over general chatbots.
Infrastructure & RuntimeRunning Kimi K3 From SSDs on a MacBook Pro: The Storage Tradeoff
Deltafin streams Kimi K3 weights from SSDs to run on 64 GB Macs, but self-reported benchmarks vary widely, limiting it to batch workloads rather than interactive use.
