The Groundy archive · Page 41 of 43
Browse Groundy's complete archive of 1027 articles on AI, developer tools and infrastructure. Page 41 of 43.
961–984 of 1027 articles · Newest first
An ACL 2026 Findings paper finds multi-agent LLM brainstorming collapses because agents share models, prompts, and context, not because topologies are too dense.
LiteRT-LM v0.10.1 ships Gemma 4 with Qualcomm NPU acceleration, but Google stripped MTP heads from public weights, locking peak Gemma 4 throughput to its own runtime.
Chinese models accounted for 41% of downloads on Hugging Face in the platform's Spring 2026 ecosystem audit, surpassing the US.
Alibaba's dense Qwen3.6-27B outperforms its MoE sibling on coding benchmarks, trading predictable inference latency for a larger memory footprint than sparse alternatives.
Three CVEs scoring up to 9.8 reveal a structural flaw: MCP's local-host trust model lacks authentication primitives for networked multi-tenant deployments.
EU battery rules improve repair rights without promising a snap-off battery in every new phone.
The ACP Agent Registry lets developers install AI coding agents once across JetBrains and Zed. Here's what the migration path looks like and whether to commit.
Atlassian's data contribution policy sends Jira and Confluence content to AI training by default. Here's the exact settings path to opt out before August 17.
GitHub shipped `gh skill` in public preview on April 16, 2026. Here's how the command works, what the open Agent Skills spec promises, and why the ecosystem is already compromised.
OpenRAG combines Langflow, OpenSearch, and Docling into a single deployable RAG platform. Here's how it compares to managed services like Pinecone.
The Temporal API reached Stage 4 and is shipping in browsers. Here's what it fixes about JavaScript's notoriously broken Date object and how to use it.
People form real emotional bonds with AI companions. When models update or shut down, users experience genuine grief, a psychological and ethical crisis point.
MLX and llama.cpp both run quantized LLMs on Apple Silicon unified memory. Here is what each project documents, and how to measure which wins on your Mac.
Prefill and decode disaggregation lets LLM serving separate prompt processing from token generation. Its value depends on latency targets, KV transfer, and worker utilization.
SWE-bench Verified tests AI agents on 500 real GitHub bug fixes. Learn what 'resolved 49%' means, how scoring works, and the benchmark's critical blind spots.
Compare DeepSeek, Qwen, Kimi, Doubao, ERNIE and GLM through dated benchmarks, license terms, context windows, API pricing and practical workload fit.
Claude Code in GitHub Actions is safest when it is a narrow, reviewable automation, not a privileged bot that edits every pull request.
A local R1 memory plan needs the chosen weight artifact, the distill's own configuration, and the intended context length.
CodeSpeak compiles structured English into production code via LLMs. Kotlin creator Andrey Breslav's bet: ad hoc prompting is too ambiguous for serious software development.
Fish Audio's open-source S2 TTS hit SOTA in March 2026 with sub-100ms latency and 80+ languages, challenging ElevenLabs' commercial pricing and exposing licensing gaps.
Google's LiteRT (formerly TensorFlow Lite) powers on-device GenAI on Android, Chrome, and Pixel. What developers need to know about private, offline inference.
Alibaba's page-agent embeds an LLM agent in any web page with one script tag for natural language DOM control, with no browser extension or headless browser.
AI tools beat radiologists on narrow imaging tasks like lung nodule detection, yet only about 2% of U.S. radiology practices use them. The evidence, gaps, and barriers.
Hindsight by vectorize-io is an open-source agent memory system that replaces stateless retrieval with structured, time-aware memory networks, achieving 91.4% on LongMemEval and showing what genuine agent learning looks like at the architecture level.