
OpenAI ライブストリーム
OpenAIがライブストリーム配信イベントを開催します。放送中に具体的な発表、新製品発表、またはデモンストレーションが明かされる予定です。
OpenAIが前回予告なしのライブストリームをやった時、GPT-4 Turboをドロップして、一晩で価格設定を完全に変えました

Peeps are always asking which local model is best. That question is loaded and totally depends on the task you're asking of it. Llama2 for example is old but still useful for summarizing YouTube transcripts into 10 bullet points. I don't code with it obviously, but it works well for that. So, I built my own benchmarking tool to test local models on my client codebases. SWE Bench and similar tools test only Python gate-based tasks. They do not care whether the model writes slop or creates addit