Skip to main content
Watch: Grok Bot Built My AI Video Arena While I Tested 8 Models

AI

177 items

104 posts, 62 tools, 11 guides

Tool
Claude Fable 5

Anthropic's first generally available Mythos-class model, released June 9, 2026. 1M context, 128K max output, $10/$50 per million tokens. Built for long-horizon agentic work.

Tool
Claude Opus 4.8

Anthropic's Opus model released May 28, 2026, and its recommended default until Opus 5.5 shipped in September 2026. 1M context, 128K output, $5/$25 per million tokens.

Tool
DeepSeek V4

DeepSeek's open-weights frontier family, previewed April 24, 2026. V4-Pro is 1.6T total / 49B active params; V4-Flash is 284B / 13B. 1M context standard. Weights on Hugging Face.

Tool
OpenCode

Open-source AI coding agent for terminal, desktop, and IDE. Works with 75+ LLM providers including Claude, GPT, Gemini, and local models. Runs parallel sessions on one project.

Tool
Jules

Google's asynchronous coding agent. Point it at a GitHub repo, it clones to a cloud VM, plans with Gemini, and opens a pull request. Tiered plans from 15 to 300 tasks per day.

Tool
Goose

Free, open-source (Apache-2.0) AI agent built in Rust, governed by the Agentic AI Foundation. Desktop app, CLI, and API. Bring any of 15+ model providers or an existing subscription.

Tool
Conductor

Mac app for running parallel Claude Code, Codex, and Cursor agents in isolated workspaces. Watch every agent work at once, then review and merge their changes.

Tool
LiteLLM

Open-source AI gateway: call 100+ LLM providers in the OpenAI format via a Python SDK or proxy. Spend tracking, budgets, rate limiting, load balancing, and fallbacks built in.

Blog
DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster

DiffusionGemma is Google's 26B MoE open model that generates 256-token blocks in parallel. What diffusion generation means for latency and local inference.

Tool
DeepSeek-TUI

Open-source (MIT) terminal coding agent, renamed Codewhale, with Plan, Work, and Operate modes, approval postures, /undo and /restore, receipts, MCP servers, sub-agents, and a local runtime HTTP API. Provider-neutral: 40+ built-in provider routes plus local models, no longer DeepSeek by default.

Blog
Claude Opus 4.7: The Developer's Guide to Anthropic's New Flagship

Claude Opus 4.7 developer guide: what changed, pricing, SDK usage, prompt caching, when to pick Opus vs Sonnet or Haiku, and migration notes from 4.6.

Blog
Flagship: Cloudflare Feature Flags for AI Apps

Cloudflare Flagship is an OpenFeature-native flag service evaluated at the edge. What it actually ships, how to use it for model rollouts and kill switches, with code from Cloudflare's announcement.

Blog
Mercury 2 Developer Guide: Building With a Diffusion LLM in Production

Mercury 2 developer guide: the OpenAI-compatible API, tool use, structured outputs, reasoning levels, and when a diffusion LLM beats an autoregressive one.

Blog
SAM 3.1: Realtime Video Segmentation in Apps

SAM 3.1 makes Meta's Segment Anything fast enough for realtime video. How to wire it into a production pipeline and the gotchas to plan for.

Blog
Vercel's Agentic Infrastructure Stack Explained

Vercel's agentic infrastructure explained: what the announcement actually names, how AI Gateway, Sandbox, Workflows and Flags compose, with code checked against the SDKs.

Tool
Pydantic

The most widely used data validation library for Python, and the de facto standard. Type-hint-driven models, fast Rust-based core (v2), and the foundation of FastAPI, LangChain, and most Python AI tooling.

Blog
DESIGN.md: The Contract That Keeps AI Agents On Brand

A repo-root DESIGN.md gives Claude Code, Codex, and other agents the design rules they need to honor so generated UI does not drift into generic territory.

Tool
Claude Haiku 4.5

Anthropic's smallest Claude 4.5 model, released October 2025 and succeeded by Haiku 5.5 in October 2026. Sonnet 4-level coding at one-third the cost. $1/$5 per million tokens.

Tool
Qwen3-Coder

Alibaba's open-weight coding model, released in 2025. 480B total parameters, 35B active (MoE). Native 256K context, extends to 1M. Apache 2.0 license. Built for agentic coding.

Tool
DeepSeek V3.2

DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.

PreviousPage 3 of 9Next
AI Development Stack

Get Smarter About AI Dev

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.

One email per weekReal code, not theoryFree forever