Skip to content

Accept All すべて承認

Cline Blog

15 stories

Cline BlogTools11,840 TPS on a single GPU NVIDIA released Nemotron 3.5 Super VL on October 15, and we reached 11,840 aggregate output tokens/sec on one GB300 with 256 concurrent requests .

Cline BlogToolsBuilding Faster AI Agents with Jev Decision Models and Cline Modern agents are built around a classic loop: send the LLM a prompt, it thinks, it processes, and it responds back through a chat-based API.

Cline BlogToolsCline Agents Harness Unlocks Benchmark-Leading Performance from NVIDIA Nemotron 3.5 Super VL Open weights models have become the new frontier of achieving intelligence more efficiently, and we are super excited to see how the latest NVIDIA Nemotron 3.5 Super VL model continues to push the…

Cline BlogToolsCline Desktop: An open-source app for open-weight models Meet Cline Desktop, an early version of our open-source app for open-weight models. Cline started as a VS Code extension and is now used by more than 11 million developers.

Cline BlogToolsHow We Migrated 11 Million Users to Cline's Biggest Harness Upgrade The Cline extension was first built in 2024, right after Claude 3.5 Sonnet was released. It created one of the very first agentic coding experiences used by millions of developers, but both models…

Cline BlogToolsDeepSeek wins IMO Gold on 12 cents We wanted to know the cheapest possible way to win an IMO gold medal, so we ran eight models against IMO 2026 problems in Cline and had the proofs graded blind. The answer was 12 cents .

Cline BlogToolsBuilding a code review agent on the Cline loop At Cline, LLMs have helped us ramp up our ability to ship, allowing a team of our size to write code without compromise on quality.

Cline BlogToolsOpen-sourcing evals for open-weight agents Preface With new model releases like Fable and Gpt-5.6 Sol, it's becoming increasingly clear that closed-weight models are becoming a very expensive commodity, leaving us at the mercy of frontier…

Cline BlogToolsNVIDIA Nemotron 3.5 Lightning just landed in Cline NVIDIA just released Nemotron 3.5 Lightning, a new customizable open model built for always-on agents and it is now available in Cline for FREE.

Cline BlogToolsTop 5 Open Weight Models That Matter to Developers in 2026 The perspective for open weight models has changed significantly in 2026. In just the past few months, labs like DeepSeek, Z.ai, Moonshot AI, MiniMax, and Qwen have released models that developers…

Cline BlogToolsRecursive Self Improvement for Coding Agents Preface Recursive self-improvement is the idea that models can iterate and improve on themselves to unlock singularity. We have achieved a version of that at Cline.

Cline BlogToolsHow to Save Millions by Self-Hosting LLMs Preface If you believe that cheap open weight models are the future then this blog is for you, we all know the why, but I will show you the how grounded in the economics behind it.

Cline BlogToolsClinePass, Best of Value for Open-Weight models Since developers started building in the agentic coding space, the logic felt simple: pay a premium for top-tier tokens, get the best result. The model was the moat. The model was the product.

Cline BlogToolsExtending the Cline loop with plugins and hooks An agent loop is a system around an LLM that lets it observe, decide, act, and repeat until a goal is met.

Cline BlogToolsIntroducing Cline SDK: the upgraded agent runtime, and we rebuilt Cline upon it Before “agents” became a buzzword, Cline was the first real agentic coding experience. Cline started with the VSCode extension and helped a generation of developers step into AI coding.

On the calendar

予定 · Conferences and launch events, this week's stories from each corner of the industry, and what its press is covering — in English

On view

This week, from that corner the newest stories from the corner of the industry you picked

The wire their own posts, translated

How code moves in 2026 from the industry's own reports

Sources

Fetched every six hours, linked to the original

About

The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo