Keep on to blur preview images; turn off to show them clearly
RT @MattWalshBlog: It's an empirical fact that basically everything in our day to day lives has gotten worse over the years. The quality of…
🇪🇺 https://t.co/NdorAWrhrB @euacc 📸 https://t.co/lAyoqmT9Hv $115K/m 🏡 https://t.co/1oqUgfDEsx $36K/m 🛰 https://t.co/ZHSvI2wRou $42K/m 🌍 https://t.co/UXK5AFra0o $14K/m 👙 https://t.co/RyXpqGvdBB $14K/m 💾 https://t.co/M1hEUBB6da $6K
Majestic alps. I should go more often to the peaks 🏔️ But in Switzerland 🇨🇭
🌏 RCBI advisor & offshore services for HNWI, business owners with a focus on:🇨🇭🇲🇾🇰🇳🇵🇾🇻🇺🇳🇷🇵🇦🇱🇻🇦🇪🇭🇰 | Geopolitics | Healthy lifestyle
but then you get the reversed fear: how a large part of the population has been so easily one-shotted by slop free models, with code, data, infra held by duct tape.
Artisanal baker of reasoning models @pleiasfr
拆解了 60 篇高质量油管口播稿，用 5 个常用模型跑了一遍调研, 发现了一些有趣的点 T1 梯队（GLM, Sonnet, k2）: 直男秘书, 执行力强但略显“老实”，往往需要用长 Prompt 来“超频”才能更好发挥. 如果你对某个领域烂熟于心, 那么效果就很棒, GLM 速度回快一些, 有些描述比较模糊, 可以二次指正细化. Sonnet 记录笔记很扎实. T0 梯队（Opus, Gemini）：具备洞察力的“咨询顾问”。擅长听懂弦外之音，能从散点中提炼框架，特别适合做 Pattern 识别和重构。提示词写起来相对精简一些, 自适应能力也很强. PS: 感觉洁面奶3的幻觉蛮严重的, 需要强调, 不要谄媚, 告诉我真实看法. 有的时候为了经济, 会结合 T0 和 T1 来用 1. 用 T0 写 Prompt 骨架 2. 投喂给 T1 试运作 3. 人工抽样, 看下是否和我的预期有差别 4. 结果回流给 T0 优化 5. 丢给 T1 量产 你们可以试试这个玩法.
🖥️ Indie Maker 🛠️ 星球「海哥和他的小伙伴们」 📌 油管「海拉鲁编程客」 🌸 沦为程序员的段子手/猫咪
WXPush - 基于 Cloudflare Workers 搭建的轻量级微信公众号模板消息推送服务，作者还制作了详细视频教学。 ✅ 完全免费 ✅ 每天 10 万次额度 个人用不完 ✅ 真正的微信原生弹窗 + 声音提醒 ✅ 支持多用户 ✅ 跳转稳定 ✅ 可无限换皮肤 https://t.co/973kMG6DIe
🧠在家居士 | 🥦素食者 | 🏃🏻马拉松爱好者 | 💰省钱小能手 | 搭🪜技术资深学者 | 👨💻科技宅 | 🆕更新狂 | 🆅 六边型战五渣
RT @ripplebrain: You don't have to remind them, this principle is a cornerstone of Nuclear Orthodoxy and the divine struggle of Slavic Jiha…
We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1