#编码

隆重推出 Claude Opus 5。 这是一个深思熟虑且主动的模型，以一半的价格接近 Fable 5 的前沿智能。

隆重推出 Claude Opus 5。 这是一个深思熟虑且主动的模型，以一半的价格接近 Fable 5 的前沿智能。

Ling-3.0-flash is now free on OpenCode inclusionAI's latest model optimized for token efficiency

The gap between flash and frontier models keeps shrinking. Ling 3.0 Flash is live on Kilo now, free for a limited time, and it's punching way above its weight for agentic coding tasks. Big thanks to @NovitaAI for the speed behind it!

http://x.com/i/article/2079482473818333184

A delivery orchestration platform that supplies FedEx, estimated 7 to 8 months to rebuild their core system. We delivered in 3.5 months with 2 engineers and 122 merged pull requests in the first 90 days. I want to walk through how, because "we used AI and it was faster" doesn't help anyone. Their codebase had real users, real logistics operations, and real consequences if something broke. This is brownfield, not a weekend prototype demo. Week one, we didn't write code. We scanned the entire repo and built a knowledge graph: markdown files documenting every module, dependency, data flow, and domain term. Our agents read that graph before touching anything. Teams skip this constantly. They point an agent at a repo, hand it a ticket, and get code that compiles but misunderstands the architecture. I've seen it across 100+ engagements. When someone says "AI doesn't work on our codebase," they almost always skipped context acquisition. Every ticket ran a six-step loop: define, spec, plan, implement, test, document. The agent handles about 90% of code generation. A senior engineer reviews every PR, and nothing merges unless they can verify it, explain it, and debug it without the agent. We call that the V.U.E. gate. The 50% time reduction came from three things: upfront context eliminated false starts, the agent handled mechanical coding so engineers focused on design and review, and tight spec-to-PR discipline kept scope from drifting. AI compute: about $200 per developer per month. Their CTO called our pod the "top performing team" inside the company. Both engineers got discretionary bonuses, twice. That's what our Velocity Framework was built for.

We summarized the key remarks from DeepSeek founder Liang Wenfeng during their investor meeting. The core topics include open-source strategy, cost reduction, and AGI. https://www.thexpin.com/p/the-deepseek-doctrine

This is insanely cool. Set this up in Grok Build! Unity shipped a free terminal Unity CLI for coding agents, CI, and custom tooling. MCP stays supported, the CLI includes MCP Mode for existing MCP agents, and Unity says both the CLI and MCP are free with no concurrency limits on the MCP server. Dan got Grok 4.5 via Grok Build to install the CLI, build a 3D scene, and export a video. "Same session shipped a playable macOS Island Explorer with Poly Haven CC0 trees, rocks, and cliffs, Crest FFT ocean with shoreline foam, irregular hills, grounded props, FPS walk, and a half-size performance pass when the scene got heavy." -- Daniel Farinax

Laguna S 2.1 performs at GLM-5.2 level on building popular games with 6x fewer params! We gave three local models the same task: build three popular arcade games that play themselves. Each game is one self-contained HTML file with a bot that plays it. Prompts: – Geometry Dash – Doodle Jump – Air Hockey Outputs: Laguna S 2.1: 10.3K tokens GLM-5.2: 26.4K tokens Hy3: 10.4K tokens Laguna held its quality against a 753B model. We think Laguna's Geometry Dash looked the best of the three, the cube clears every spike and block. GLM won Air Hockey. Its table looked the most detailed of all. Hy3 was the only model that added shooting to its Doodle Jump. But Laguna is the only model in our benchmark that runs on a MacBook with 128GB!