Megumin retweetledi
Megumin
193 posts

Megumin retweetledi
Megumin retweetledi

筛选了一下能买到的信息
大概有:
车队 / 拼车
plus
team / 团队
会员
20X
5x
image 2
codex
Token
DeepSeek鼻祖
欢迎补充(禁止黄推,你们在我评论区刷了200多条都被ban了心里没数吗????)
叫我阿杭@Astronaut_1216
现在买GPT pro的闲鱼黑话是啥啊?? 我都搜不到了
中文

@realNyarime 学校在名单里吧, 我申请的时候不在,后来我校进名单了,有github pro,但是无法修改billing 和个人信息了
中文
Megumin retweetledi

Meet Kimi K2.6: Advancing Open-Source Coding
🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)
What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on kimi.com in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code
-
🔗 API: platform.moonshot.ai
🔗 Tech blog: kimi.com/blog/kimi-k2-6
🔗 Weights & code: huggingface.co/moonshotai/Kim…

English
Megumin retweetledi
Megumin retweetledi
Megumin retweetledi

兄弟们,Claude Code 彻底本地跑起来了,零 API 费、无限刷、完全不怕数据泄露!
就两步:
- 装最新 Ollama
-装 Claude Code CLI
然后敲一行命令:
ollama launch claude
瞬间弹出熟悉界面,工具调用、代码补全全都有!
想更强就加 --model qwen3-coder,用你的显卡跑,
性能看硬件。
界面和工具调用完全一样,但使用的是开源模型(非 Anthropic 原版 Claude),能力取决于所选模型和硬件
不想再被 Anthropic 割韭菜、不想 API 账单爆炸的,赶紧试。隐私党福音来了!本地跑AI编码,爽到飞起!谁已经上手了?
中文

@shao__meng @thsottiaux 使用 codex 分析 claude code 源码的太多了吧,50多万行代码根本吃不下
中文

OpenAI Codex 又又又重置额度了
Thank you @thsottiaux 😄
昨天撸 Claude Code 源码把 Codex 额度用完,断水断电到现在,本来以为要扛到 4.3,意外惊喜,额度重置了!
这次重置的原因也很人性化:
OpenAI Codex 出现用户频繁触发速率限制的异常现象。团队尚未完全定位根因,但已采取预防性重置措施——将所有订阅层级的使用额度清零重置。
同时,Codex 团队发现并封禁了一批欺诈账户集群,成功回收了被滥用的计算资源。

Tibo@thsottiaux
Our Codex dashboards are showing increased rate of users hitting rate limits and since we don't fully understand why I have made the cautious decision of resetting the usage limits for all plans. Enjoy. I also wanted to celebrate us finding a pocket of fraudulent accounts that we banned and have helped us regain some compute. The fight against abuse never stops, but it's important to mark the moment and make it a little shared victory.
中文






















