Devin for Terminal is a local agent that works... with all frontier models, including Opus 4.7, GPT 5.5, and SWE-1.6. You can switch model mid-session, or handoff to Devin in the cloud.show more

Devin Desktop supports the Agent Client Protocol (ACP): bring... your own agents to work alongside Devin, all in one unified view.show more

You don’t have to use one model (or one... provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.show more

we compared Gemini 3.1 Pro, Opus 4.7, and GPT... 5.5 to Kimi K2.6, Xiaomi Mimo v2.5, and Qwen 3.6 Max in average, closed source are faster. GPT 5.5 and Opus 4.7 the fastest. Kimi K2.6 comes after. It keeps up thanks to its native INT4 quantization. MiMo took the longest, but the refinement and aesthetic only ranks after Gemini 3.1. as if a mini Gemini. Its slow cuz it's trained for long-horizon agentic work. Claude Opus 4.7 is blooming in a very different style, probably because Anthropic trains for taste, not just accuracy.show more

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested... three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.show more

You can now connect your OpenRouter URL directly to... the Warp Agent. OpenRouter unlocks a world of models including Anthropic, OpenAI, Gemini, DeepSeek, Kimi, and more, all with better prices and uptime. Set your URL, model, and an alias to easily switch using /model.show more

Salute to the Qwen team 🫡 We tested Qwen... 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.show more

You can set up Auto-Triage for any Slack channel... with just three clicks. To help get you started, we're offering $200 in credits when you create your first Devin Automation.show more

My first time building with Opus 4.7 and I... love it! I quickly built this Base AI Ecosystem map with names, links logos in the form of a galaxy that you can navigate through 🛰️ With some rigorous prompting, Opus 4.7 did everything for me including descriptions and logos!show more

Agreed. It's why we've been building a command center... in the Warp terminal so you don't need to learn tmux to manage agents. - All conversations are searchable from history - Close tabs and revisit later with session restore - Track both local and cloud agent runsshow more

To make it easier to migrate your workflows, we've... updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.show more

I don't think there's a single terminal ux that... handles agent swarms well With slate, you can literally use Opus 4.6 and GPT 5.4 at the exact same time But making it intuitive took a ton of work So heres a thread on how it works and how to actually use it 🧵show more

Open-weight LongCat 2.0 matched GPT-5.5 level on agentic game... dev for $0! We ran Meituan's LongCat 2.0 against cloud frontier GPT-5.5 in Kilo CLI with their agent. Same task for both - build a retro Duck Hunt game in one game.html, improved over 3 agent iterations with duck waves, ammo and physics Outputs: LongCat 2.0: 70.3K tokens, $0.00 GPT-5.5: 64.9K tokens, $0.65 LongCat kept up on graphics, physics and game logic. Ducks fly and fall when hit, the dog fetches them, ammo counts down, the waves keep coming. Both ran clean and nothing clipped. The only difference was the bill - GPT cost $0.65, LongCat ran local for $0show more

We’re shipping Devin Search, a new tool for codebase... understanding. Use Devin Search for quick questions like "how is user authentication implemented?" or turn on Deep Mode for complex asks like “draw an architecture diagram explaining our billing system”. 🧵👇show more

GPT-5.5 in Codex is built for long-session agent work.... But context still doesn't follow you across projects, agents, or teammates. ByteRover does that + Save you tokens -> No rewriting context when you switch from Claude Code to Codex. Now connecting Codex, Claude Code, OpenClaw, Hermes, and 22+ more agents. Your context moves with you. → personal context for solo work → team context for shared decisions and bug historyshow more

LongCat performed Opus 4.8 and GPT 5.5 level on... real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!show more

MCP is here! You can now give Devin access... to your favorite servers via the MCP Marketplace. Think Datadog, Linear, Sentry, Figma, and thousands more. Demos from our team + getting started 👇show more

Funny how you can do the same thing with... a local model without sending all your data to a remote cloud.show more

GPT-5.1 is now live in Warp. It’s much faster... (40% faster task completion on a subset of SWE-bench Verified) without compromising quality. GPT-5.1 is available to all Warp users, and is now the default model for all new users.show more

MRC is already deployed across all of OpenAI’s largest... supercomputers that we use to train frontier models, including our site with Oracle Cloud Infrastructure (OCI) in Abilene, Texas, and in Microsoft’s Fairwater supercomputers. MRC is now available through the Open Compute Project for the entire industry to use and build on.show more

Okay, this is seriously cool. A team from Google... DeepMind, including DeepMind Cofounder Shane Legg, published a paper "From AGI to ASI". In the paper, they include instructions for an AI agent to read along with you. You can open the paper in Codex's in-app browser and have GPT-5.5 read it with you and explain all the concepts. This is the future. AI agents will be part of the target audience, and help us to understand anything we want.show more