Showing all posts about ai ← All Posts

Humanity's Last Exam

Fascinating repo of incredibly esoteric and difficult questions that frontier models can benchmark themselves on — Opus 4.6 scores a paltry 46%. Also discussed on the New York Times.

The questions shouldn't be shared but there are 2500 of them and they're accessible via Hugging Face — so interesting!

An example question which they shared:

Hummingbirds within Apodiformes uniquely have a bilaterally paired oval bone, a sesamoid embedded in the caudolateral portion of the expanded, cruciate aponeurosis of insertion of m. depressor caudae. How many paired tendons are supported by this sesamoid bone? Answer with a number.

Anthropic understandably decided to block Openclaw from having oAuth access and I wanted to use Anthropic Extra Usage but it cost me $25 in credits in 1 day, so alas, using Anthropic for OpenClaw is a no go.

I bought the $20/month OpenAI plan and connected that to OpenClaw. We'll see. It took many hours to get things working again, but not really the fault of OpenAI but how buggy OpenClaw is...

It really makes you wonder how much OpenClaw blew up the Anthropic business model in the past 6 months. If there is 100k users using Anthropic oAuth on OpenClaw and its $15/day in costs... thats a huge hit on their margin!

Meditation, Language, and LLMs

I’ve been somewhat facetiously, somewhat seriously, somewhat jokingly, been posing a question to everyone I run into these past few months: Don’t you feel like all meaning is being scrubbed from the world? Like the Langoliers are chomping up purpose, chomping up all the things to which we’ve ascribed purpose these past hundred-thousand years? And that nothing matters?

Really, what I’m asking is: Don’t you think our contemporary education system has long needed an overhaul? That our society has long needed to reconfigure itself? That we need to stop ascribing all our meaning and purpose to being a Web Designer, or Coal Miner, or Airplane Engine Factory Foreman, or Accountant, but instead to being A Good Person, Good Parent, Good Friend, Curious Researcher, Poet, Meditator, Facilitator, or any number of other Ways of Being uncoupled from “work” as we’ve defined it since the industrial revolution? Who is safe from the hunger and capabilities of the models? Yoga instructors?

✰ Knowledge Skill

LLMs are amazing at summarizing content. Agents are amazing at doing workflows based on a simple input. I have found a huge amount of value by using OpenClaw as a "second brain."

✰ OpenClaw Agent Model Selection

Let OpenClaw plugins dynamically override which AI model handles a request, enabling cost-optimized routing based on prompt complexity or session context, amongst other things!

Teacher AI Use is Already Out of Control and It's Not Ok

I teach HS Science in the south. I can only speak for my district, buta few teacher work days in the wave of enthusiasm I'm seeing for AI tools is overwhelming. We're getting district approved ads for AI tools by email, Admin and ICs are pushing it on us, and at least half of the teaching staff seems all in at this point. I was just in a meeting with my team and one of the older teachers brought out a powerpoint for our first lesson and almost everyone agreed to use it after a quick scan- but it was missing important tested material, repetitive, and just totally airy and meaningless. Just slide after slide of the same handful of sentences rephrased with random loosely related stock photos. When I asked him if it was AI generated, he said 'of course', like it was a strange question. Then, I told the team I might go in a different direction because I wanted to avoid using AI in the classroom and the team lead made a face and told me that all of the lessons she brings for our meetings have been AI generated for the last year.

Constantly amazed at how often Product Managers jump on the AI bandwagon without full context. Eg: someone excitedly discussing the Agentic Shopify MCP when just using a simple Restful API is more than sufficient.