Introducing Magnitude. It's a coding agent that runs entirely on open models. It costs 60% less than Claude Code with no drop in performance. Try it now: npm i -g @magnitudedev/cli Here's how it works 👇

All these GLM 5.2 providers advertise 200 tok/s. Yet you try them and get 50 tok/s The top speeds are super impressive. And I love how much activity there is in the ecosystem. But it makes it really hard to get a true read of provider inference speeds under normal conditions My guess is they allocate a ton of compute to their serverless model APIs right around launch, then slowly pull it back once their score has been established. It's benchmaxxing but for providers You can see it in the Artificial Analysis chart of speeds over time. They peak right on launch day, then gradually or sometimes rapidly decline over the next few days I'm very excited for when one of these reported 200 tok/s scores holds for 7 days

It’s interesting that GLM 5.2 is in the same cost ballpark as GPT 5.5 despite costing ~5x less per token You could say it’s because GPT 5.5 is more efficient with its tokens, but I think it’s largely because GLM 5.2 is inefficient It thinks for far too long, and sometimes will spend an entire benchmark task just thinking and not taking any tool calls. This hurts performance and costs a lot There’s ways to patch this at the provider layer and when you do, GLM 5.2 token efficiency increases dramatically with no drop in performance (in fact it gets better!)

turns out firmware engineering is an awesome use case for open models talked to a founder this week doing 1B tokens a day with them. just points his agent at his execution trace and has it patch things live runs it pretty much all day. most of the work is pattern matching and does not need a frontier model. and it would hit cc rate limits anyway interesting

I don’t think you can actually run GLM 5.2 locally to do meaningful work (yet). The 2 bit quant benchmarks at 82% top-1 accuracy. That sounds great in theory until you realize that means you’re getting the “wrong” tokens ~20% of the time. Think about how quickly that compounds

clever!

it turns out if you do a lot of really good context engineering, you can get frontier intelligence for like half the price, and in some cases even better than a single frontier model

These guys (@tomgreenwald & @anderslie) build with incredible taste Highly recommend checking this out if you're building with OSS models

Excited for @wafer_ai to partner with @usemagnitude to power their coding agent with powerful open source models! Open source models are the closest to frontier LLMs they've ever been, so it's now feasible to reduce costs by 60% while maintaining quality across the board.

My friends @tomgreenwald & @anderslie made a harness designed for open source models. If you’re working with OSS models, don’t use anything but magnitude. They squeezed every last drop of performance out of their harness.

At HumanLayer, we’re on a mission to solve the AI slop code problem. In 2025 we open-sourced our Research, Plan, Implement framework, now deployed inside fortune 500s like Block and Uber - places where shipping slop is just not an option And that was just the beginning. Today, we’re opening access to HumanLayer - an Agentic IDE, collaboration platform, and building blocks for your software factory. HumanLayer enables engineers solving hard problems in complex codebases to: > move 2-3x faster across the entire SDLC (not just coding) > maintain rigorous standards for system architecture and program design Hundreds of engineers at companies of all sizes are already using HumanLayer to ship fast without sacrificing quality. I'm excited to invite you to try humanlayer today at humanlayer.com, and I'm even more excited to see what you build. @0xblacklight and I are deeply grateful to our team, our customers who give us so much incredible energy and feedback, our investors who have always been in our corner, and our friends and family who have supported us along this crazy journey if you're a staff or principal engineer trying to make AI coding work at scale for your team, we'd love to hear from you as @swyx likes to say - let's make this the year of no more slop

81% on Terminal Bench 2.1 😱