Florian Leibert 🎢

Serving config for Kimi 2.6 on 8x MI300X with DFlash speculative decoding (AMD). news.ycombinator.com/item?id=478468…

OG loop engineering: while (true) { raiseMoney() }

90s were different

Getting banned from github is the new getting banned from seeking.

I'm excited to announce the most ambitious recreation of Bloom's 2Sigma study of the last 40 years. It's funded by @reedhastings and staffed by a team of 20 of the best educators in this country. Our education team's goal is to show the largest academic gains in one year ever recorded, and we'll publish our results even if we fail. Recently, @jwdanner introduced me to @reedhastings. Most people know Reed co-founded Netflix. Fewer know he has been one of the driving forces behind improving education for the last twenty years. When Reed pitched me on recreating Bloom's famous 2-sigma problem, I felt an overwhelming sense of hope for education. Over the last few months we have moved at breakneck speed to assemble an exceptional team. Someone recently described it to me as the "Avengers of education." We are testing one question with the rigor it deserves: can elite one-on-one tutoring reproduce the largest learning gains ever measured in a controlled study? We will work with researchers from Stanford, Brown, Cornell, and other leading institutions, and we intend to be the most transparent research group in the field. That means publishing our methods, our benchmarks, and our results, whatever they show. We will invest up to $100,000 per year per student to give them the best education on the planet. If it works, the data and methods can help educators and technologists recreate these outcomes for every child. We are actively hiring tutors, engineers, and operations people to help us climb this mountain.

The challenge will be making enough progress on model quality and context window to keep up with ever growing codebases.

@jietang Vision. Then we can read papers, math texts, etc, and the model can see the figures and charts too.

@brian_armstrong @ClementDelangue I’m running both of these on mi300x amd and am super happy… imho better than current codex

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage caps, so instead of lowering caps and driving up alerts, we're moving to cheaper defaults. Note that code reviews use a diversity of models, so they can check each other's work. Better Routing – In our custom harnesses, we preprocess prompts and route to the best model for the job, considering cache hits and model pricing. For instance, you may want a frontier model for planning, but not for execution where they can be overkill. Ultimately, humans shouldn't be choosing models - AI can automate this task. Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. For example, our cache hit rate went from 5% → 60% in LibreChat once properly implemented. Keep Context Lean – Start fresh sessions when switching tasks. Scope file context narrowly. Disconnect unused tools. Don't just compact. The goal isn't fewer tokens used, it's fewer tokens wasted. Better Visibility – Our engineers can use as many tokens as they want, from whatever model they want, but we’ve made usage visible – and the more you spend on AI, the more impact we expect. The goal isn't to suppress usage. It's to build the infrastructure that makes exponential growth sustainable. Putting this into practice has cut our AI spend nearly in half, while our token usage continues to grow.

@matei_zaharia Is that single session speed? What hardware does it run on?

The Databricks inference team is 🔥

. @GoJettly is such a scam…

@Lexioryn Asking for an extension

@flo 72 hours countdown begins now

Current status: retardmaxx'in flocode (to be release within the next 72 hours [or so])

My main branch is called master

When you’re trying to do something, neither @OpenAI not @AnthropicAI want you to do their models work against you!

"It's not the persuit of happiness but the happiness of the persuit".

Claude Code 4.7 is insane. i know literally NOTHING about coding. ZERO. and i just built 3 fully functioning web apps in 30 minutes. http://localhost:3000/ http://localhost:8000/ http://localhost:5000/ check it out.

@Jason @ClementDelangue @Apple Well your buddy Dario is trying to ban that shit #wtf???

Given token economics, we really need @apple’s new ceo to go all in on workstations that can run local, open source models Ideally, with a router that can flip between local models and frontier models when the former gets stuck. And America needs an open source champion — we really should not be comfortable with the Chinese owning the open source LLM market to the extent they do

Me with $137 in my pocket worrying about SpaceX opening price so I can buy 1 share

Faaaaack