News & Insights

Guides, model updates, and perspectives on AI-powered development.

Bring Better Context with Tarsk File Workflows
Productivity

Bring Better Context with Tarsk File Workflows

Copy files into a Tarsk project, attach them to chat, and review previews before you send your next request.

August 15, 2026 · 6 min read
Project Task Automations in Tarsk
Productivity

Project Task Automations in Tarsk

Turn project tasks into repeatable work that Tarsk can start on demand or on a schedule.

August 11, 2026 · 6 min read
Kimi K3 and the Rise of Open-Weight AI
AI Models

Kimi K3 and the Rise of Open-Weight AI

Moonshot AI released Kimi K3 as the largest open-weight model ever at 2.8T parameters. The model's benchmarks, architecture, and what open weights mean for developers.

July 30, 2026 · 8 min read
Tarsk's macOS Sandbox: Safe by Default
Product Updates

Tarsk's macOS Sandbox: Safe by Default

When you tell an AI agent to run a bash command, you're handing it a shell. Tarsk's macOS Seatbelt sandbox provides kernel-level containment for bash and skill scripts, and it's on by default.

July 22, 2026 · 5 min read
Cut Your Token Costs by Splitting Planning From Code
Product Updates

Cut Your Token Costs by Splitting Planning From Code

Orchestrate mode uses a smart model to plan your task and cheap models to build it. Most users see 40 to 60 percent lower token spend on multi-file features.

July 21, 2026 · 7 min read
Connect MCP Servers with OAuth in Tarsk
Product Updates

Connect MCP Servers with OAuth in Tarsk

Tarsk now supports OAuth for remote MCP servers, so your agent can sign in to services with your account instead of static tokens. Here is how to add Sentry from the marketplace.

July 20, 2026 · 6 min read
Microcompaction: Cut Mid-Turn Token Cost
Product Updates

Microcompaction: Cut Mid-Turn Token Cost

Older tool outputs used to ride every later model call in an agent turn. Microcompaction digests that stack once context gets tight, so you pay less and finish longer tasks.

July 17, 2026 · 7 min read
Tarsk's Recommended Models: July 2026
AI Models

Tarsk's Recommended Models: July 2026

Four major model launches in ten days. Claude Sonnet 5, GPT-5.6 Sol, GPT-5.6 Luna, and Grok 4.5 each changed the cost-to-capability math. Here's how to pick.

July 15, 2026 · 6 min read
Save Money and Tokens With Compression
Product Updates

Save Money and Tokens With Compression

The tool calls in your coding session account for up to 55% of your token spend. Here is how you can reduce that cost and speed up your responses using compression.

July 1, 2026 · 7 min read
Tarsk updates: dual chat, voice, skills
Product Updates

Tarsk updates: dual chat, voice, skills

Tarsk updates this week include dual chat, faster voice input, a new skills catalog, an integrated terminal, browser element selection, and a long list of workflow fixes.

June 26, 2026 · 7 min read
New faster streaming voice input
Product Updates

New faster streaming voice input

Tarsk now uses Vosk for voice input. It streams your text in real time as you speak -- no pause, no wait. Runs locally, works offline, supports 20+ languages.

June 19, 2026 · 6 min read
GLM-5.2: Open-Weights Model Challenges Claude Opus on Coding
AI Models

GLM-5.2: Open-Weights Model Challenges Claude Opus on Coding

Zhipu AI's GLM-5.2 is a 744B open-weights model with MIT license and 1M context that beats GPT-5.5 on coding benchmarks at one-quarter the cost of Opus 4.8.

June 18, 2026 · 7 min read
What's New in Tarsk: Mid-June 2026
Product Updates

What's New in Tarsk: Mid-June 2026

MCP server editing for local and remote, model selector grouped by provider with price sorting, long-running agent confirmation, folder projects, and a floating review chat in the diff view.

June 13, 2026 · 8 min read
Claude Fable 5 in Tarsk
AI Models

Claude Fable 5 in Tarsk

Anthropic's Mythos-class model ships with 1M context and long-horizon agent skills. Eleven Tarsk providers list claude-fable-5 today, from Anthropic and Bedrock to OpenRouter and GitLab Duo.

June 10, 2026 · 7 min read
NVIDIA Nemotron 3 in Tarsk
AI Models

NVIDIA Nemotron 3 in Tarsk

Nemotron 3 ships as Nano, Super, and Ultra: open MoE models for agent workloads. Nine Tarsk providers already list them, including OpenRouter and Together AI for Ultra.

June 6, 2026 · 6 min read
What's New in Tarsk: June 2026
Product Updates

What's New in Tarsk: June 2026

Settings got a navigation overhaul, context usage now breaks down by category, chat drafts persist across tabs, and you can preview markdown or open your repo in Cursor with one click.

June 6, 2026 · 7 min read
Local Voice-to-Text: Privacy in Your Browser
Product Updates

Local Voice-to-Text: Privacy in Your Browser

Tarsk now supports voice-to-text. It runs Whisper entirely locally in your browser using WebAssembly, keeping your spoken words completely private.

June 2, 2026 · 4 min read
NVIDIA Nemotron-3 Ultra: A Very Large Model
AI Models

NVIDIA Nemotron-3 Ultra: A Very Large Model

NVIDIA launched Nemotron-3 Ultra at Computex 2026. It has 550 billion parameters, uses Mamba-2 layers, and does not cost as much as you might think.

June 1, 2026 · 5 min read
Introducing Claude Opus 4.8
AI Models

Introducing Claude Opus 4.8

Anthropic's most capable model yet brings adaptive thinking, production-ready code generation, and long-running agentic workflows to developers everywhere. Here's what it means for your workflow.

May 28, 2026 · 6 min read