Pangram Labs released Pangram 4, an AI text classifier that detects whether text was written by humans or AI systems. The model achieves 99.16% accuracy and can now identify mixed human-AI writing and fine-grained edits better than its predecessor.

• AUROC of 0.9916 with 0.0041% false positive rate and 0.3396% false negative rate
• Can distinguish fine-grained edits and detect interleaved AI assistance in co-authored text
• Shows improved robustness to adversarial attacks and better generalization to out-of-distribution data

This article breaks down Andrej Karpathy’s zero-dependency, 243-line GPT implementation in plain Python. It explains how each part—tokenizer, autograd engine, embeddings, attention mechanism, residual connections, and MLP—mirrors a full-scale transformer on a tiny dataset of baby names.

• Karpathy's microGPT implements a full GPT—tokenizer, autograd engine, transformer, training loop—in just 243 lines of pure Python with zero external dependencies beyond os, math, random and argparse.
• A ~40-line custom autograd engine (Value class) replicates PyTorch's backward-pass mechanics via topological graph traversal.
• The toy model trains on baby names using a tiny architecture (16-dim embeddings, seq length 8, single layer, 4 attention heads) totaling about 4,000 parameters.
• The same core transformer math—embeddings, RMSNorm, attention, MLP—scales up unchanged to power trillion-parameter models like GPT-4.

Deep Think with Confidence (DeepConf) is introduced as a method to improve reasoning efficiency and performance in large language models by using internal confidence signals to filter out low-quality reasoning traces. It requires no additional training or tuning and can be easily integrated into existing systems. Evaluations show significant accuracy improvements and a reduction in generated tokens on various reasoning tasks.

• DeepConf uses internal confidence signals to filter out low-quality reasoning traces without any additional training or tuning
• It integrates easily into existing LLM systems
• Evaluations show significant accuracy improvements alongside a reduction in generated tokens across various reasoning tasks