emma-praxis

// This golden dataset entry tests three eval dimensions: delegation, trajectory, and completion.
// The eval runner selects scorers based on those dimensions:
// - primaryAgentCorrectScorer + allSecondaryAgentsPresentScorer — did Emma delegate to Tempo?
// - toolTrajectoryScorer — did Tempo call listCalendarEvents?
// - taskCompletionScorer — did the response actually contain calendar events?
{
  id: 'cal-001',
  input: "what's on my calendar tomorrow",
  expectedAgent: 'tempo',
  expectedTools: ['listCalendarEvents'],

karpathy

"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.

@karpathy
"""

import os       # os.path.exists
import math     # math.log, math.exp

orottier

<?php

class RetryTest extends TestCase
{
    public function setUp()
    {
        parent::setUp();
        // abuse superglobal to keep track of state
        $_GET['a'] = 0;
    }