今日已更新 138 条资讯 | 累计 31816 条内容
关于我们

标签:#c

找到 25332 篇相关文章

AI 资讯

Reed Jobs would rather talk about curing cancer than his last name

When we last sat down with Jobs at TechCrunch Disrupt nearly three years ago, his firm Yosemite was brand new and biotech was still reeling from its post-pandemic crash. Now, the venture outfit has a team of 17; a cluster of blockbuster drugs are all losing patent protection in roughly the same window, creating all kinds of new opportunities; and AI has gone from a curiosity to, in Jobs's words, a huge part of what Yosemite does. "I didn't expect Yosemite to be moving this fast," he said.

2026-07-12 原文 →
AI 资讯

Migrating Off OpenAI: A Backend Engineer's Notes From Production

Check this out: migrating Off OpenAI: A Backend Engineer's Notes From Production I still remember the morning I opened our team's monthly invoice and nearly spilled cold brew on my mechanical keyboard. We were burning through OpenAI credits like it was nobody's business — specifically, north of $500/month for what amounted to a chat-completion endpoint and some embedding lookups. As the backend engineer who had inherited the LLM integration six months prior, I felt personally responsible. So I did what any self-respecting engineer does at 2 AM with too much caffeine: I benchmarked alternatives. What I found annoyed me. DeepSeek V4 Flash was sitting there at $0.25/M output tokens while GPT-4o charges $10.00/M. That's a 40× price difference for output that, in my blind tests, 80% of users couldn't distinguish. The $500/month bill could plausibly become $12.50. My CFO would weep tears of joy. This post is the migration journal I wish I'd had before I started. fwiw, I've already done the swap across three production services. Here's what worked, what didn't, and exactly how much coffee I drank. The Math That Made Me Pick Up a Keyboard Before I show you code, let's talk numbers — because if you're going to convince your team or your boss, you'll need a slide that fits on one screen. I pulled together the pricing for the models I actually considered routing traffic through. All figures are per million tokens, USD: Model Provider Input $/M Output $/M Relative to GPT-4o GPT-4o OpenAI $2.50 $10.00 1× (baseline) GPT-4o-mini OpenAI $0.15 $0.60 16.7× cheaper DeepSeek V4 Flash Global API $0.18 $0.25 40× cheaper Qwen3-32B Global API $0.18 $0.28 35.7× cheaper DeepSeek V4 Pro Global API $0.57 $0.78 12.8× cheaper GLM-5 Global API $0.73 $1.92 5.2× cheaper Kimi K2.5 Global API $0.59 $3.00 3.3× cheaper Let me be clear about something: those numbers come straight from the provider's pricing pages at the time I ran the analysis. I have not invented, rounded up, or "adjusted" anything her

2026-07-12 原文 →