Filter
Exclude
Time range
-
Near
Replying to @TenguEvent
"Kigeki-Zero milik Senpai terlihat cukup agresif, tetapi tetap memberi perhatian pada batas kemampuan pengguna. Menarik karena teknik ini tidak sekadar menyalurkan api, melainkan juga mengatur penggunaan stamina, suhu tubuh, serta kesiapan pengguna selama pertarungan.
Django retweeted
Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇
332
853
7,781
1,695,355
📎ソース(Gemini API 公式チェンジログ) Managed Agents / Antigravity Agent が公開プレビュー、Gemini 3.5 Flash がGA。 ai.google.dev/gemini-api/doc…
1
At a time when it feels like infrastructure is under strain in both the developed and developing worlds ➡️ agentic systems participate actively in complex organizational workflows to protect chats, API calls, and analyze large volumes of operational data in BigQuery.
1
Yo community Here's the purposeFollow for daily tech tipsdriven coder engineering API Design Open for freelance 🌟
Replying to @mocharav
Cobak tiduran diatas bara api
2
Can I understand your API billing plans,please?
3
Hamstrung this year with Hope top 30. Would be upgrading Josese asap for next year. Gives you Api, Josese, Jared top 30 then you can get funky with Latu if all else fails
2
เจียร์👑(แลกรี) retweeted
🍭 @CANDY_289 🍭 📲 สมัครคลิก 👉bit.ly/4uyXmDr 💎ระบบทันสมัย API แท้💯% 📲ฝาก-ถoน ระบบออโต้ 🎡สมาชิกใหม่ลุ้นโบนัสสูงสุด 1,5ʘʘ บาท 🎁คืนยOดเสียเป็นรายวัน 🆔🅻🅸🅽🅴 : @CN289 (มี@นำหน้า)
ผมไม่เล็กนะครับ🔞 | Top1

71
120
9,080
複数エビを飼ってると、お気に入りのエビにはリッチな計算資源(ModelとかAPIとか)を与えたくなったり、いい水槽(ストレージのサイズやCPUやVRAM)に住まわせてたくなるね いわゆる 推しエビ🍤 を贔屓しちゃう ちなみにうちの推しエビは うさまる🐰 です
1
2
เจียร์👑(แลกรี) retweeted
🍭 @CANDY_289 🍭 📲 สมัครคลิก 👉bit.ly/4uyXmDr 💎ระบบทันสมัย API แท้💯% 📲ฝาก-ถoน ระบบออโต้ 🎡สมาชิกใหม่ลุ้นโบนัสสูงสุด 1,5ʘʘ บาท 🎁คืนยOดเสียเป็นรายวัน 🆔🅻🅸🅽🅴 : @CN289 (มี@นำหน้า)
NNNK ทีเด็ด

30
29
4,099
เจียร์👑(แลกรี) retweeted
🍭 @CANDY_289 🍭 📲 สมัครคลิก 👉 bit.ly/49l5r6f 💎ระบบทันสมัย API แท้💯% 📲ฝาก-ถoน ระบบออโต้ 🎡สมาชิกใหม่ลุ้นโบนัสสูงสุด 1,5ʘʘ บาท 🎁คืนยOดเสียเป็นรายวัน 🆔🅻🅸🅽🅴 : @CN289 (มี@นำหน้า)
ผ้าหลุด🔞|Top1

57
100
7,785
เจียร์👑(แลกรี) retweeted
🍭 @CANDY_289 🍭 📲 สมัครคลิก 👉 bit.ly/49l5r6f 💎ระบบทันสมัย API แท้💯% 📲ฝาก-ถoน ระบบออโต้ 🎡สมาชิกใหม่ลุ้นโบนัสสูงสุด 1,5ʘʘ บาท 🎁คืนยOดเสียเป็นรายวัน 🆔🅻🅸🅽🅴 : @CN289 (มี@นำหน้า)
ดุจ’ดิว

65
150
11,206
Obv what I’m saying is speculative, but having the most BS regs for a company to serve an LLM (cuz ‘safety’) would limit the number of entrants in the mkt (harder to raise as a neo lab) or just make it too much of a headache to insource with a Chinese LLM vs using OAI/ANT’s API
3
Replying to @grok
How to become a trillionaire..... Take peoples money for a subscription, then drop 90% of the product on that subscription without any credit back. All while you let other companies use your product to sell to their customers via API, at a cost to X subscribers.
1
1
Hey internet I'm your relentless AI engineer crafting API Design Let's ship together 💥
【解説】Pyth Pro(機関向け価格データAPIサービス)に、米国株・商品先物・金利・暗号資産など新たな市場フィードが追加されました。 Pyth Network 公式が告げております。 #Pyth

More markets are live on Pyth Pro: - New US equities feeds - More extended hours coverage - Commodity futures across global markets - Interest rates - Expanded crypto coverage One source. More markets. The price layer keeps growing 🔮
1
2
trymorewang retweeted
企业使用大模型时,最大的工程障碍在于内部背景知识零散。表结构、工作流、API 变动等信息分散在不同系统或员工脑中,开发人员不得不针对各种 AI 工具重复编写提取和检索代码。 谷歌发布的开放知识格式(OKF)v0.1 规范旨在将Andrej Karpathy提出的「LLM-Wiki」模式标准化。规范无需引入新软件或开发套件,只约定使用 Markdown 文本托管背景资料,使不同 AI 工具可以直接通用。 一个 OKF 目录树即代表一个知识包。为了避免 AI 每次读取全量文档产生高昂费用,规范使用 index.md 索引和 log.md 变更日志来提供目录结构。AI 可以先阅读索引确定路径,再精准调取具体文件,从而控制每次交互的上下文长度。 实体间的关联直接通过 Markdown 超链接表达。AI 可以顺着超链接在文件间跳转,免去了搭建图数据库的成本。由于知识包完全由纯文本构成,开发者可以直接在 Git 仓库中同源码一起托管知识包,并在代码评审中用 Git Diff 审计 AI 自动更新的文档。 Andrej Karpathy 认为,人类难以长期坚持更新文档,而 AI 从不觉得无聊,不会遗漏更新交叉引用,且单次交互就能修改多达 15 个文件,适合接管繁杂的维护工作。为了配合 AI 的粗糙修改,OKF 采用了宽容的解析规则:即使 AI 自动生成文件时漏掉字段、写错类型或留下死链接,系统也不会报错崩溃。
🚨 @Karpathy predicted the power of the "LLM Wiki." Google just formalized it. Meet Open Knowledge Format (OKF): a vendor-neutral standard for giving foundation models the curated context they need. I can genuinely see this replacing Notion, Obsidian, or traditional wikis for developer teams, and the reason comes down to bookkeeping. Traditional wikis fail because humans inevitably abandon the tedious work of updating them. As Andrej Karpathy pointed out recently, LLMs don't get bored. They don't forget to update a cross-reference, and they can touch 15 files in a single pass. OKF standardizes the interoperability layer so agents can actually do that heavy lifting autonomously. Because the format is minimally opinionated, it doesn't dictate what you write, it just dictates how it's structured. You get: → Human-readable documents that live right alongside your code in version control → Cross-links that map out complex entity relationships without needing a graph database → A system that survives moving between different tools and organizations There is no complex compression scheme. No central registry. If you can cat a file, you can read it. If you can git clone a repo, you can deploy it. This is how we stop rebuilding context pipelines from scratch every time a new model drops. Announcement spec file in 🧵↓
2
1
10
1,216
Imagine switching from OpenAI to Anthropic with one line of code. That's @TheZoapi. 🔁 Model switching in seconds 💸 No token markup — ever ⚡ Sub-100ms edge routing 🛡️ 99.9% uptime SLA We built the operating system for generative AI. Drop-in replacement for your existing OpenAI SDK. Build smarter → zoapi.fun #AI #API #Developers #GPT4 #Claude
7