Page 5 of 100

Read

Deep dives into AI agents, coding tools, and building with LLMs.

1189 articles844 topics

All AI Agents News Claude Code Developer Tools AI Coding Hacker News Anthropic AI Models OpenAI Open Source Claude Codex View all 844 topics

7 min read

Local LLM Speed by Hardware: What llmspeed Gets Right

llmspeed estimates tokens per second for 30 machines and 15 models. What its numbers mean, the memory-bandwidth rule behind them, and why prefill matters for coding agents.

Local Models Hardware Benchmarks

13 min read

MCP Client Features: Sampling, Elicitation and Roots Explained

MCP sampling, elicitation and roots explained against the 2026-07-28 spec, with JSON-RPC examples and which of 24 clients support each one.

MCP Model Context Protocol AI Agents

8 min read

MiniMax M2.5 and M2.7 Retirement: How to Move to M3 Before November 18

MiniMax closes M2.5 and M2.7 to new users on October 19, 2026 and retires them on November 18. Which model id to switch to, what it costs, and the exact API change.

minimax migration llm-apis

12 min read

OpenAI Is Winding Down Fine-Tuning: Where to Move Your Fine-Tunes (October 2026)

OpenAI stops new fine-tuning jobs on January 6, 2027, and every base model it still lets you tune shuts down by January 14. The dates, what keeps serving, where fine-tuning still exists, which providers let you download weights, and a migration checklist.

fine-tuning openai model-deprecations

8 min read

GPT-Live Decisions: Native Delegation and Transcript Triggers

GPT-Live can now call the Decisions API itself, mid-sentence. How native delegation and transcript triggers work, the session config, and the events to handle.

OpenAI Realtime Voice Voice AI

13 min read

Prompt Caching Across AI Providers: Prices, TTLs and Setup

Prompt caching across OpenAI, Anthropic, Gemini, DeepSeek, Mistral, xAI and Qwen: prices, TTLs, setup code. A reused 100K prefix costs 71-93% less.

Prompt Caching Cost Optimization OpenAI

7 min read

REA vs leanrea: Skill or MCP for Reverse Engineering Agents?

leanrea is an 8 KB skill pitched as a replacement for the REA (Reverse Engineer Anything) MCP server. What its benchmark shows, what it skips, and which to install.

News MCP Agent Skills

13 min read

Structured Outputs Across AI APIs: OpenAI, Claude, Gemini (2026)

97 of 167 models we track enforce a JSON schema on output. Request shapes, schema limits and refusal handling for OpenAI, Claude, Gemini and Mistral.

AI Models APIs TypeScript

11 min read

Vertex AI Shutdowns This Week: Gemini 2.5 on October 20, 16 Open Models on October 21

Google Cloud retires Gemini 2.5 Pro, Flash and Flash-Lite on Vertex AI on October 20, 2026, and 16 open MaaS models the next day. Replacement ids, prices, and the code change.

google vertex-ai migration

14 min read

Which AI APIs Train on Your Data? Free Tiers, Paid APIs and Retention, Checked Against 18 Providers' Own Terms (October 2026)

Free tiers are where training happens: Google's unpaid quota outside the EEA, Switzerland and the UK, Mistral's Free mode, and some OpenRouter free models. Paid APIs mostly say no. Retention is a separate question, and four providers' own docs disagree with themselves.

privacy data-retention free-tier