Category: tech > ai

Google DeepMind's Gemma 4 targets mobile and IoT deployment with multimodal input, native function calling for agents, and fine-tuning support.

Google released Gemma 4 as four Apache 2.0 models with native vision, function calling, reasoning, and audio on edge, closing the open-weights gap.

Google DeepMind's Gemma 4 is an open-weights family for on-device and edge deployment with multimodal input, native function calling, and multilingual context.

An interactive deep-dive into Claude Code's internals: the agent loop, 40+ tools, multi-agent orchestration, slash commands, mapped from the open source.

Ollama 0.18 now uses Apple MLX on Apple Silicon for faster local LLM inference, with NVFP4 quantization, better KV cache, and Qwen3.5-35B-A3B in preview.

A drop-in CLAUDE.md targeting Claude's verbose defaults (sycophantic openers, restated questions, em dashes) to cut output tokens roughly 63% per prompt.

Three CLI browser agents for Claude Code: Playwright CLI (lowest tokens), Firecrawl Interact (automation plus scraping), Vercel Agent Browser (leaner, faster).

The .claude/ folder controls Claude Code behavior through instructions, permissions, commands, skills, and subagents. Keep CLAUDE.md under 200 lines.

Stripe ships 1,300 agent-authored PRs a week, enabled by a decade of cloud dev environments, docs, and CI tooling that give agents a human-like workflow.

PipesHub is an open-source, self-hostable workplace AI platform that unifies search across Google Workspace, Microsoft 365, Slack, Jira, and Confluence.

A developer reverse-engineered Claude Code's binary and found a built but server-gated feature: speculative execution pre-runs your next action in a sandbox.

Claude Code now supports scheduled autonomous tasks that run on a cron-like schedule in the cloud, with access to GitHub repos and MCP connectors.

Ollama launched tiered cloud plans alongside local support. GPU-time-based pricing means efficiency gains from better hardware benefit you directly.

Cloudflare's Dynamic Worker Loader spins up V8 sandboxes in milliseconds, making per-request AI agent isolation 100x faster than containers.

GSD solves context window degradation by breaking work into atomic plans executed in fresh subagent contexts with parallel wave execution.

Claude Code's Dream feature automatically cleans memory files by resolving contradictions, merging duplicates, and removing stale information.

LocalAI is a drop-in replacement for OpenAI and Anthropic APIs, running 35+ model backends locally on any hardware with built-in AI agents.

Everything Claude Code is an optimization system with 28 agents, 125 skills, and 60 commands that can cut AI coding costs by 60% or more.

CLI-Anything auto-generates CLI wrappers for desktop software like GIMP and Blender, making them controllable by AI agents like Claude Code.

NanoClaw runs Claude Code in isolated containers connected to WhatsApp and Telegram, with only 15 source files and 3,900 lines of code.