Six months into customizing my own Claude Code harness, I've settled on assuming Anthropic and OpenAI will just handle all of it, except turning my own flows into skills.
[dead]
Is the attention explanation of why the model tells like this? I've seen that there are many discussions about this. (Image attention visualizations were not that good I think)
[flagged]
Ah, success rate here are scored by an agentic classifier. And uncertain outcomes are excluded from the graph. The thing measured and grading it comes from the same house. In my setup, review agent pass work that an…
I only get web search from Claude Code when I ask, only one of my last 8 sessions accessed the web at all. But they were the case of Opus here. Curious what Fable 5.1 model does instead of Opus.
I tried to make a memory system in Claude Code (make it behave like a human from the perspective of memory) using markdown files and indexing plus hooks. But, retrieval is not as good as a human and since keywords are…
We can control it (claude.md and plus use 'rules') but, it would be better if not verbose before I set it. yeah
Yeah. That's why people these days avoid long descriptions and instead keep things as short as possible. in my experience, it seems like LLM can't recognize (or less attention value) unless it's structured in a…
API Error: 529 Overloaded in some sessions - South Korea Still does not work in these sessions
Six months into customizing my own Claude Code harness, I've settled on assuming Anthropic and OpenAI will just handle all of it, except turning my own flows into skills.
[dead]
Is the attention explanation of why the model tells like this? I've seen that there are many discussions about this. (Image attention visualizations were not that good I think)
[dead]
[flagged]
Ah, success rate here are scored by an agentic classifier. And uncertain outcomes are excluded from the graph. The thing measured and grading it comes from the same house. In my setup, review agent pass work that an…
I only get web search from Claude Code when I ask, only one of my last 8 sessions accessed the web at all. But they were the case of Opus here. Curious what Fable 5.1 model does instead of Opus.
[dead]
I tried to make a memory system in Claude Code (make it behave like a human from the perspective of memory) using markdown files and indexing plus hooks. But, retrieval is not as good as a human and since keywords are…
We can control it (claude.md and plus use 'rules') but, it would be better if not verbose before I set it. yeah
[dead]
[dead]
Yeah. That's why people these days avoid long descriptions and instead keep things as short as possible. in my experience, it seems like LLM can't recognize (or less attention value) unless it's structured in a…
API Error: 529 Overloaded in some sessions - South Korea Still does not work in these sessions