FRAMEWIREIndonesiaUpdated Oct 3Live wire
0:00 / 0:00

Most AI trading bots give one model all the jobs

So I split it into a crew Opus 5.5 reads the market and writes the plan Astra 6 builds the code and tests it plain code places the order and holds the stop at -1.2% every 5 min candle gets a score from 0 to 1 under 0.60 it

AidanOct 210
0:00 / 0:00

Everyone is posting Opus 5.5 + Jev.

Few explain what Jev actually is. It's not another chatbot. It never writes a sentence. You send it a question with the possible answers defined in advance. It sends back a typed decision, a probability and a confidence score. That's the

werdenOct 25
0:00 / 0:00

This is my quantitized Qwen3.8 Flash Next 2.6bpw using specialized engine for EXL3 compression, inspired from Strata.

Running on single RTX 3090 and 64GB RAM. I got like 60-70 tok/s and 2,100 tok/s prefill peak with 256k context. Its been running like 3-4 hour with Eiffel Tower

lackonendesOct 2
0:00 / 0:00

Same bug. same model. same prompt.

One finished in 4:35. one took 18:20. guess what the difference was. same flaky test took opus 18 minutes and two questions to me. with jev it took 4:35 and it never stopped once. all it took was these 6 lines in CLAUDE.md. [with jev

rodonOct 23