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)
NVidia basically abandonned various tegra related SBCs. But this one runs DGOS which they have a few $b worth of hardware floating around in various clouds and is a derivative of ubuntu.
Seems like this is MUCH more likely to have at least decent support, I think the current DGOS is based on ubuntu 22.04 LTS.
As others have said, this came after historically significant low popularity and mounting political pressures. His government faced criticism over falling poll numbers, by-election losses, and a broken agreement with the NDP. Tensions with the US and internal dissent within the Liberal party added to his challenges.
One of the final nails in the coffin was the resignation of Chrystia Freeland, his last standing ally and Finance Minister.
Reading through the two 2024 threads I'm struck that most predictions a) were completely wrong b) reflected more what people wanted to happen rather than what was likely.
Edit: now that I've read through this thread I'll add c) were much more hopeful than this year's predictions.
This is mostly just for fun and will be mostly wrong because none of the people who are making predictions take it seriously. And none of the upvoters take it seriously either.
There is a discipline to making predictions (Phil Tetlock has observed a few traits: avoiding base rate fallacies, working in probabilities not binaries, making falsifiable predictions, and continuously updating).
None of the predictions here do that, so we shouldn’t expect any kind of reasonable hit rate.
It reflects the mood, which tells me all I need to know about things like short term stock changes. In reality nobody can predict the future. My predictions have historically also been way off, but what is surprising to me is that people don't reflect on their misses. For the most part I've given up in predicting anything, at best I will look at trends and see if there's something there or not.
But with that said I will now post my predictions for 2025 :-).
Yes. People are not stupid. It's one thing to have a phone in your purse. It's another to have something on your head and eyes, like how is anyone going to agree to that? Sure if it was very cheap you'd find some interested folks.
I remember being called outdated, a contrarian and 'in the way of progress' on this site when I expressed doubt that the Vision Pro would be 'the next iPhone', as people on this site put it. I was told that our way of working would change within the year and that everybody would be scrambling to emulate Apple.
I don't mind enthusiasm and excitement, but for others to directly make such bold claims then put others down was a disappointing experience for me here.
Could it be the top comments even though most voted are also most commented and more divisive and controversial? And the most boring comments are somewhere at the back? Hence big amount of failed predictions at the top.
I was eeading an article on this a while ago tgat i sadly cant find but you should expect these threads to be wildly incorrect because people can read everyone elses predictiobs and be swayed by them. The wisdom of the crowd only appears to work when nobody gets to see otger results first and then the median position is wgat is usually most accurate.
I think I recently (few days ago, that is in the last few days of 2024) saw a Vsauce video/short about this regarding a trial trying to use the wisdom of the crowd to get an accurate number for the amount of jelly beans in a large jar. The trial was similarly skewed by "open" predictions, concretely people being allowed to give their predictions while in the presence of their group (friends/family/etc). Unfortunately I cannot seem to find it, but your comment reminded me of that.
After losing my shirt some years earlier I announced to my wife that I was ready to get into the buying shares again. She agreed, but only if I bought good ones this time.
