HACKER NEWS

New research from MIT reveals that LLMs identify speakers by writing style, not by tags - meaning attackers who sound like the system effectively become the system. The findings explain why prompt injection remains unsolved.

Dan Abramov's explainer on ATProto architecture is making the rounds. The core insight: Bluesky's protocol separates hosting from applications in a way that Mastodon-style federation fundamentally cannot. Here's what that means for developers.

The new wrangler deploy --temporary flag creates ephemeral Cloudflare accounts for AI agents. 60-minute deployments, no OAuth, no browser - just deploy and claim later.

New benchmark data shows GPT-5.5 hallucinates 86% of the time when it does not know the answer - versus 28% for the open-weights GLM-5.2. The numbers challenge the assumption that bigger models equal more reliable output.

Modern LLMs now use MoE routing, mixed attention variants, and fused vision encoders. The simple transformer stack is gone - here's what replaced it and why it matters for developers.

A deep dive into DuckDB's architecture - columnar storage, vectorized execution, and zero-copy design that lets it compete with million-dollar clusters on a laptop.

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's most anticipated performance feature is finally landing. Value classes eliminate object identity overhead and enable dense memory layouts - here's what changes.

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

A YC W25 startup open-sources CADAM, a browser-based tool that converts natural language to parametric OpenSCAD models. HN debate: is text-to-CAD genuinely useful or just another demo?

Auto-installing tree-sitter grammars, built-in markdown mode, window layout commands, and more - the upcoming Emacs release absorbs features that used to require external packages.

Alex Ellis shares real production experience running local LLMs: $12k hardware investment, 2-3 month ROI, and why treating local models as Opus substitutes misses the point entirely.

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 open-sourced Lore, a centralized version control system designed for binary-heavy game projects. It uses Merkle trees, on-demand file hydration, and native chunked storage to handle terabyte-scale repos that Git struggles with.

The IETF published RFC 10008 defining a new HTTP QUERY method - GET with a request body. It is safe, idempotent, cacheable, and solves the longstanding problem of complex queries hitting URL length limits.

GitHub is filling with multi-agent frameworks, skills, and coding harnesses. The useful lesson is not that every team needs a swarm. It is that every agent needs receipts: tests, logs, diffs, and reviewable checkpoints.

Flue is trending because it names the part of agent infrastructure that is becoming product-critical: the programmable harness around the model.

Open Design is trending because it turns Claude Code, Codex, Cursor, Gemini, and other CLIs into a design engine. The useful lesson is not design automation. It is artifact-first agent wrappers.