With DeepSWE benchmarks being released and showing a drastic difference to what open-source benchmarks are showing, they took a deeper look into how the harnesses affect the model, and the results are quite surprising. — TIMESTAMPS: 0:00 Opus 4.8 is here! 00:13 Looking at the benchmarks 00:44 DeepSWE, the closed-source benchmark 01:06 The real results 01:55 Claude Code vs API usage 03:22 claude -p kills developer potential to get the most out of Claude — Unlock the full potential of your online presence with Kabarza and Samuel—experts in web design and development (respectively), powered by cutting-edge AI solutions. We blend creative design with advanced tech to deliver smart, high-impact websites that stand out. Ready to elevate your business? Contact us today and see what AI-driven innovation can do for you! LINKS & RESOURCES: Website: https://cmdaishow.com Check out Kabarza's amazing work: https://kabarza.com Visit Samuel's website for more: https://samuelgregory.co.uk 📷 Follow on Instagram: https://www.instagram.com/cmdaishow — HASHTAGS: #opus #claude #claudecode #deepswe #ai #podcast #aidesign #aidevelopment #vibecoding #webdesign #webdevelopment #ainews #webnews #designnews #devnews
Cmd+ AI