Sim ini pada dasarnya membiarkan model perbatasan berlomba dalam kondisi yang sama.
They received state updates every 5 seconds and had to make real-time decisions. Result: Gemini Argon first, GPT Astra second, Claude Opus timed out, Qwen grounded itself.
Ini benar-benar gila. Elon Musk baru saja mengatakan Grok 5 akan mengalahkan Opus 5.5 dalam 2 hingga 3 bulan.
This is how his senior engineer already works with Grok Bot: "You spend the tokens once to set up the codebase, so even the dumbest agent does a good job Then you stop babysitting. 200+
Mereka membangun agen AI dalam 20 menit dan menjualnya ke Anthropic seharga $100k - dan di Stanford menunjukkan cara mengulanginya dari awal
02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 -
Saya menjalankan 5 tes nyata yang sama pada setiap model Claude saat ini
Fable 5.2, Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5. Same prompts. Identical computers. Judged blind by a non-Claude model. The newest, most expensive model did not win. Tests by petergyang. Full video:
Sudah sampai ujung arsip
Semua Claude Opus 5