Ah never mind I looked it up. The MW blocks exist within the Litecoin blocks so they a processed at the same rate.

Do MWEBs accumulate at the same speed as the main chain?

Agentic coding tools take too much control from the human. Whenever I try them it feels wrong and the results are a mess. They discourage human oversight which degrades the quality of the code.

I'm still using aider because it is not agentic and it lets me stay in the loop. I'm maintaining a fork with some quality of life improvements (including a single-binary build) here if you're interested: https://github.com/chr15m/aider

Here's my .aider.config.yml:

```yaml
auto-commits: false # prevents aider from doing git commits
gitignore: false
notifications: true
show-model-warnings: false
watch-files: true
auto-lint: true
read: [/home/chrism/dev/ai-context/AGENTS.md, README.md, AGENTS.md, .context/*]
```

Agree, it's a tool. I am finding it useful when used in a disciplined way with a human in the loop at literally every step. I think the current tooling gives the LLM far too much leeway in general.

I did some research and testing with gpt-oss-20b and llama-4-maverick. They don't compare with Claude but could definitely handle some tasks like extracting structured information from articles, DevOps, routine coding tasks, smart OCR etc.

The Chinese open models suffer from censorship on certain topics, but there is a model where somebody trained Qwen on Deepseek outputs and it appears to be "abilterated" and will respond to those topics, and is pretty good overall. I'm going to run some of these models locally and will do a video/write-up about that.

That's a great point. LLMs are helping people overengineer stuff nobody wants, even harder.