Got curious about this year’s Fields Medal. Watched a couple of explainer videos on the Kakeya conjecture. I have particular trouble seeing the connection between Kakeya and Harmonics.
5M tokens later, I’m still clueless. The game Fable built seems to repeat one of the videos almost step by step.
Normally, you’d prompt an LLM with your question and ask it to explain. But I don’t know what I don’t know, and I have a hard time articulating that gap. So what then?
Suggestions? (not looking for more explainers, I want to learn how to learn with AI)
I'm surprised Stanford Law would go along with this over-reaching press release title. How about "For common first-year contracts-law questions, law professors preferred AI-generated answers to professor-generated answers"
The revised title is spot on. It's odd to me how academics are trying to sound like top research labs' CEOs trying to pump valuations by overreaching claims.
I use Pico with LLM code gen for new projects. As you probably know, LLMs are predisposed to Tailwind and coding for industrial strength on any tiniest projects. The trick is to feed it the whole Pico docs as context and prompt it (i.e. in your CLAUDE.md) to use Pico explicitly.
Did you do anything fancy to get the whole Pico docs into context? I see on their website that their docs are split up across a bunch of pages, did you copy+paste each one into a large prompt document? I was hoping to see a single-page docs download but I didn't find one.
I used Claude Code to understand the source code of Claude Code:
1. Tool-Based Action Framework
- Tools implement a common interface (Tool.ts) with standard methods
- Central registry in tools.ts manages tool availability and permissions
- Tools are categorized as read-only or stateful, affecting execution strategy
2. Agent Orchestration
- query.ts serves as the orchestration engine that:
- Identifies tool use requests in Claude's responses
- Manages permissions and serializes/deserializes tool data
- Schedules concurrent or serial tool execution based on tool type
- Feeds tool results back to Claude in a recursive loop
3. AgentTool Implementation
- Enables recursive agent capabilities via sub-agent spawning
- Sub-agents run with controlled permissions (typically read-only)
- Each agent invocation is stateless and returns a single result
- Implements progress streaming via async generators
4. Execution Flow
- User query → Claude response → Tool use requests → Permission checks
- Tool execution → Results normalized → Results fed back to Claude
- Process repeats with Claude potentially using additional tools
5. Architectural Patterns
- Async generators for streaming results and maintaining responsiveness
- Hierarchical permission model controlling tool access
- Normalized message formats ensuring consistent communication
- Logging chains for tracking agent activities
- Context management with optional compression (/compact)
So I did what every AI fan would do: asked Fable 5 to do the research and build an educational game https://github.com/Quantisan/kakeya-game
5M tokens later, I’m still clueless. The game Fable built seems to repeat one of the videos almost step by step.
Normally, you’d prompt an LLM with your question and ask it to explain. But I don’t know what I don’t know, and I have a hard time articulating that gap. So what then?
Suggestions? (not looking for more explainers, I want to learn how to learn with AI)