Back to all articles
GPT-5
2 articles
OpenAI Releases GPT-5: First Model to Surpass Human Experts on SWE-Bench
OpenAI's latest flagship model achieves 87.3% on SWE-Bench, marking the first time an AI system has consistently outperformed senior software engineers on real-world GitHub issues. The model is available immediately in ChatGPT and via API.
The 2025 Prompt Engineering Guide: 12 Techniques That Actually Work with GPT-5
Forget everything you learned about prompting in 2023. GPT-5 and Claude 4 respond differently. Here are the 12 prompting techniques that produce the best results with current models.