I think the other thread got flagged.

I tried using the Github VSCode Copilot because I have some credits. It will be better to wait for Claude Code to be fixed. In other words, Claude Code broken is still orders of magnitude better than Github VSCode Copilot.

I'll notice that the trading model will filter out bear down trends which is very, very helpful but it doesn't trade short. I'll ask the coding agent to find several academic research papers about trading once intraday during a down trend -- a single scalping. It will return with ~10 references. It will recreate the model, do statistical analysis, and create a search grid backtest. This will immediately give information if there is any alpha. If there is, it will iterate integrating the concept into the existing trading model.

It has enough information that it will continue to iterate for the next several hours.

It's all happening in a black box. I have no idea. My concern isn't trading but rather to get it to continuously improve unsupervised without lying or hallucinating.

Interesting. I'm not familiar with ClickHouse. I've been manually triggering compression and continuous aggregates have been a huge boon. The database has been the least of my concerns. Can you tell me more about it?