
GPT-5.5 Has a 3x Higher Hallucination Rate Than MIT-Licensed GLM-5.2
GPT-5.5 hallucinates 86% of the time on AA-Omniscience when it does not know, versus 28% for MIT-licensed GLM-5.2. What the metric measures and why it matters.
337 articles - page 28 of 28

GPT-5.5 hallucinates 86% of the time on AA-Omniscience when it does not know, versus 28% for MIT-licensed GLM-5.2. What the metric measures and why it matters.

LLM architectures got complicated: MoE routing, mixed attention variants and integrated vision encoders replaced the simple transformer. What changed and why.

DuckDB internals explained: columnar storage, vectorized execution and an in-process design that let it rival costly clusters on a laptop, plus what HN says.

Most developers only know .gitignore, but Git offers two other ignore mechanisms for local workflows and machine-wide patterns. Here's when to use each.

Java value classes (JEP 401) arrive in JDK 28 as a preview, removing object identity overhead for dense memory layouts. What changes in your code.

MCP's new Enterprise-Managed Authorization removes per-user OAuth friction. Anthropic, Okta, Figma, and Linear ship centralized auth for AI agent tooling.

Adam (YC W25) open-sources CADAM, a browser tool that turns text into parametric OpenSCAD models, and HN debates whether text-to-CAD is useful or a demo.

Emacs 31 features worth daily driving - auto-installed tree-sitter grammars, a built-in markdown mode, window layout commands and better minibuffer completion.

Local Qwen vs Claude Opus: Alex Ellis on running local LLMs in production, a 2-3 month hardware payback, and why local models are specialists, not substitutes.

The Transformer co-creator leaves Google DeepMind for OpenAI just two years after Google paid $2.7 billion to bring him back from Character.AI.

Epic Games Lore is open-source version control for binary-heavy game repos, using Merkle trees and on-demand hydration to handle what Git struggles with.

RFC 10008 defines the HTTP QUERY method - GET with a request body. It is safe, idempotent and cacheable, and avoids URL length limits for complex queries.
Showing 325-336 of 336 articles

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 844 topics
Browse All Topics