Simultaneous speech is best.

What a time. I am back here genuinely wishing for OpenAI to release a great model, because without stiff competition, it feels like Anthropic has completely lost its mind.

Care to elaborate? I jumped ship when 5.4 first released, have things gotten worse?

Has anyone here used Kimi for actual work?

I tried it once, although it looks amazing on benchmarks, my experience was just okay-ish.

On the other hand, Qwen 3.6 is really good. It’s still not close to Opus, but it’s easily on par with Sonnet.

Yes. You’re using Kimi if you use the composer-2 model in cursor. It’s great. Plan in state of the art. Execute in composer-2

Before GLM-5.1, I was going back and forth between Opus 4.5 and Kimi 4.5 and having very good results with Kimi.

I've used Kimi K2.5 when I run out of Codex quota. It does small and medium things OK. But if I work on complex things, I'll later have to spend two days cleaning up the mess with Codex. Hopefully 2.6 does better.

Anthropic must be loving it. It's free money.

Recently, Anthropic has been making bad decisions after bad decisions.

looks like opus have been nerfed from day1

Interactive tutorial - https://diffusion.fyi/tutorials/fundamentals?ch=0

I’m struggling to understand the recent wave of backlash against MCP. As a standard, it elegantly solves a very real set of integration problems without forcing you to buy into a massive framework.

It provides a unified way to connect tools (whether local via stdio or remote via HTTP), handles bidirectional JSON-RPC communication natively, and forces tools to be explicit about their capabilities, which is exactly what you want for managing LLM context and agentic workflows.

This current anti-MCP hype train feels highly reminiscent of the recent phase where people started badmouthing JSON in favor of the latest niche markup language. It’s just hype driven contrarianism trying to reinvent the wheel.

I don't even fully understand what people are suggesting instead. That we use CLI tools for everything? There are lots of things I do and tools I use that cli would be very inefficient for interacting with.

The "Junior Trap" is real: if you offload your thinking to Claude or GPT-4, you’re hitting "Done" for the day, but you’re accruing massive Learning Debt. You aren't building the failure-pattern recognition that actually makes an engineer valuable.

In a world where "Code is no longer a skill," the only way to survive is to stop being a "Prompt Operator" and start being a "System Auditor." If you can’t explain the trade-offs of the architectural pattern the AI just gave you, you aren't an engineer, you're just the person holding the screwdriver while the machine builds the house.