Urgent.News

What's breaking now, across thousands of outlets.

AI

JEV assisted LLM Trading

We gave our LLM trading bot an auditor that never sees the chart Every hour, on the hour, a vision model looks at three forex charts and decides whether our bot should buy, sell, or sit out. It has been doing this with real money since May. As of last Saturday, something finally grades its reasoning. This post is about the grader. The bot, briefly It's a Python script called gemini_snap_flash .…

The writer introduces a trading bot named gemini_snap_flash, a Python script that makes hourly decisions on forex trades. This bot relies on an AI grader called JEV, a System-One model from TypeSafe, which checks the bot's directional calls for consistency. The grader operates in a shadow mode behind a switch, with no impact on the trading process until activated.

Once activated, JEV records chart images and JEV's verdict for each trade decision, and compares the predicted direction with the bot's actual trade direction. If the bot's decisions are consistently coherent with JEV's verdicts, the bot may be a promising addition to the trading fleet. The article also mentions that JEV is being tested and that its implementation is not yet active in production.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

A model doesn't read text: what a tokenizer decides for you

Originally published at cchinchilla.dev . Part 1 of From code to weights, a 12-part series on ML fundamentals for engineers. A language model has never seen a letter. It sees integers.

  • Tokenizer converts text into list of ids
  • Determined during model's training phase
  • Cannot be altered after model training

Why Claude Code keeps writing shell commands that fail on your Mac

Disclaimer: AI helped me write this since I am not that good with words :) Claude wrote this, mid-task, while refactoring something unrelated: sed -i 's/old/new/' config.yml It's correct.

  • Claude Code writes failing shell commands on Mac due to zsh vs Bash mismatch
  • Bash runs commands using zsh login shell on macOS Catalina and later
  • Claude Code assumes GNU tools, macOS uses BSD tools causing execution errors

Seven Controls to Put in Place Before an AI Agent Gets Production Access

AI agents cross a line that ordinary chat systems do not: they connect probabilistic decisions to real actions. An agent that can read mail, update a record, run a tool, or spend money is part of your…

  • Distinguish between reading data, recommending actions, and executing them with separate checkpoints
  • Assign each tool narrow permissions: limited resources, operations, duration, and environment

More from Sunday 20 September →