*gets up on soap box* With the announcement of this new "code mode" from Anthropic and Cloudflare, I've gotta rant about LLMs, MCP, and tool-calling for a second Let's all remember where this started LLMs were bad at writing JSON So OpenAI asked us to write good JSON schemas & OpenAPI specs But LLMs sucked at tool calling, so it didn't matter. OpenAPI specs were too long, so everyone wrote custom subsets Then LLMs got good at tool calling (yay!) but everyone had to integrate differently with every LLM Then MCP comes along and promises a write-once-integrate everywhere story. It's OpenAPI all over again. MCP is just a OpenAPI with slightly different formatting, and no real justification for doing the same work we did to make OpenAPI specs and but different MCP itself goes through a lot of iteration. Every company ships MCP servers. Hype is through the roof. Yet use of MCP use is super niche But now we hear MCP has problems. It uses way too many tokens. It's not composable. So now Cloudflare and Anthropic tell us it's better to use "code mode", where we have the model write code directly Now this next part sounds like a joke, but it's not. They generate a TypeScript SDK based on the MCP server, and then ask the LLM to write code using that SDK Are you kidding me? After all this, we want the LLM to use the SAME EXACT INTERFACE that human programmers use? I already had a good SDK at the beginning of all this, automatically generated from my OpenAPI spec (shout-out @StainlessAPI) Why did we do all this tool calling nonsense? Can LLMs effectively write JSON and use SDKs now? The central thesis of my rant is that OpenAI and Anthropic are platforms and they run "app stores" but they don't take this responsibility and opportunity seriously. And it's been this way for years. The quality bar is so much lower than the rest of the stuff they ship. They need to invest like Apple does in Swift and XCode. They think they're an API company like Stripe, but their a platform company like an OS. I, as a developer, don't want to build a custom chatgpt clone for my domain. I want to ship chatgpt and claude apps so folks can access my service from the AI they already use Thanks for coming to my TED talk

6 months ago @Sentry acquired our company & since then I've been experimenting a lot with AI I wrote up some of my thoughts on vibe coding & dealing with "AiDHD" josh.ing/blog/aidhd

The new 1 Trillion parameter Kimi K2 Thinking model runs well on 2 M3 Ultras in its native format - no loss in quality! The model was quantization aware trained (qat) at int4. Here it generated ~3500 tokens at 15 toks/sec using pipeline-parallelism in mlx-lm:

MoonshotAI has released Kimi K2 Thinking, a new reasoning variant of Kimi K2 that achieves #1 in the Tau2 Bench Telecom agentic benchmark and is potentially the new leading open weights model Kimi K2 Thinking is one of the largest open weights models ever, at 1T total parameters with 32B active. K2 Thinking is the first reasoning model release within @Kimi_Moonshot's Kimi K2 model family, following non-reasoning Kimi K2 Instruct models released previously in July and September 2025. Key takeaways: ➤ Strong performance on agentic tasks: Kimi K2 Thinking achieves 93% in 𝜏²-Bench Telecom, an agentic tool use benchmark where the model acts as a customer service agent. This is the highest score we have independently measured. Tool use in long horizon agentic contexts was a strength of Kimi K2 Instruct and it appears this new Thinking variant makes substantial gains ➤ Reasoning variant of Kimi K2 Instruct: The model, as per its naming, is a reasoning variant of Kimi K2 Instruct. The model has the same architecture and same number of parameters (though different precision) as Kimi K2 Instruct and like K2 Instruct only supports text as an input (and output) modality ➤ 1T parameters but INT4 instead of FP8: Unlike Moonshot’s prior Kimi K2 Instruct releases that used FP8 precision, this model has been released natively in INT4 precision. Moonshot used quantization aware training in the post-training phase to achieve this. The impact of this is that K2 Thinking is only ~594GB, compared to just over 1TB for K2 Instruct and K2 Instruct 0905 - which translates into efficiency gains for inference and training. A potential reason for INT4 is that pre-Blackwell NVIDIA GPUs do not have support for FP4, making INT4 more suitable for achieving efficiency gains on earlier hardware. Our full set of Artificial Analysis Intelligence Index benchmarks are in progress and we will provide an update as soon as they are complete.

🚨The new cloaked "Polaris Alpha" model on @OpenRouterAI appears to be an OpenAI model. It also has configurable reasoning effort (Low/Med/High). GPT-5.1 or Codex Mini are contenders for what this might be. h/t @DavidSZD1

Introducing the File Search Tool in the Gemini API, our hosted RAG solution with free storage and free query time embeddings 💾 We are super excited about this new approach and think it will dramatically simplify the path to context aware AI systems, more details in 🧵

I've been getting a lot of value using coding agents for code research tasks recently - I have a dedicated simonw/research GitHub repo and I frequently have them run detailed experiments and write up the results. Here's how I'm doing that + some examples: simonwillison.net/2025/Nov/6…