S.C.L

[ollama @ollama]

Run Ornith with Ollama:

ollama run ornith

For coding, use it with Claude or Pi:

ollama launch claude --model ornith

ollama launch pi --model ornith

For the more capable 35B model, use:

ollama launch claude --model ornith:35b

[Ornith @ornith_]

Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.

Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks including:
✅Terminal-Bench 2.1(77.5)
✅SWE-Bench(82.4 on verified, 62.2 on pro, 78.9 on Multilingual)
✅NL2Repo(48.2)
✅SWE Atlas(41.2 on QnA, 42.6 RF, 39.1 TW)
✅ClawEval(77.1)

Post-trained on top of gemma4 and qwen3.5, Ornith-1.0 employs a novel self-improving training strategy in which reinforcement learning is used to generate not only solution rollouts, but also the task-specific scaffolds that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model generate higher-quality solutions in agentic coding.😎

All models are released under the MIT license, enabling full commercial and research use.

📖Tech Blog: https://t.co/qT9N2HYWFn
🤗Huggingface: https://t.co/PRrwqjeBtM

[Avid @Av1dlive]

Andrej Karpathy quietly shipped the best second brain idea in years

not an app. a pattern.

let an llm maintain a wiki of your notes. you dump sources, it reads them, links them, files them. knowledge compounds like interest.

someone built it into a free claude code plugin. setup is two commands:

claude plugin marketplace add AgriciDaniel/claude-obsidian
claude plugin install claude-obsidian@agricidaniel-claude-obsidian

then open obsidian, open claude code in the same folder, type /wiki.

that's it. your notes are now queryable by claude and they get richer every time you read something.

bookmark this. best thing you'll build this weekend.

[Ren @Ryrenz]

Youtube 昨天才发布的最新 Hermes-Agent 配置与实战教程出炉！

作者 Craig Hewitt（Castos AI 创始人，搭过几十个商用 Agent），31 分钟手把手带你从零配置一个常驻云端、永久记忆、会自己写 Skill 的 Hermes 智能体——让你的生产力翻十倍！

章节：

00:00 为什么选 Hermes
01:09 Hermes 是目前最强的开源智能体框架
02:32 为什么要跑在云上，不是 Mac Mini
03:56 用 Docker 一键部署，把它关进"盒子"
06:07 Hermes 自带网页仪表盘
07:01 模型-harness 匹配：给 Hermes 配 GPT-5.5
09:25 SOUL.md：给智能体一个持久人格
12:27 永久会话记忆，越用越懂你
13:36 Skill：会自己写，但要小心别乱写
18:42 用 Web UI 替代终端
19:44 接 Telegram，��时随地指挥它
22:39 Cron 定时任务：每天早 6 点自动简报
23:47 Profile 子智能体：一人变一个团队
27:01 MCP 与插件，安全边界别松
29:06 Config 配置文件藏在哪
29:56 看板：让智能体把活摆上台面

30 分钟，带你搭出一个帮你提高十倍生产力的爱马仕。

[Codez @0xCodez]

https://t.co/eJB3TgyJwV

[实践哥MinLi @MinLiBuilds]

https://t.co/lx2bdjgH5E

[Garry Tan @garrytan]

https://t.co/EVPCod6rxu

[Claude @claudeai]

Build and deploy your agents through the Claude Console, Claude Code, or our new CLI: https://t.co/E9xQ7xd4rG

Read more on the blog: https://t.co/omWjJ4fK88

[Claude @claudeai]

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.

It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.

Now in public beta on the Claude Platform.

[Muhammad Ayan @socialwithaayan]

🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build.

48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub.

It's called Graphify. One command. Any folder. Full knowledge graph.

Point it at any folder. Run /graphify inside Claude Code. Walk away.

Here is what comes out the other side:

-> A navigable knowledge graph of everything in that folder
-> An Obsidian vault with backlinked articles
-> A wiki that starts at index. md and maps every concept cluster
-> Plain English Q&A over your entire codebase or research folder

You can ask it things like:

"What calls this function?"
"What connects these two concepts?"
"What are the most important nodes in this project?"

No vector database. No setup. No config files.

The token efficiency number is what got me:

71.5x fewer tokens per query compared to reading raw files.

That is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases.

What it supports:

-> Code in 13 programming languages
-> PDFs
-> Images via Claude Vision
-> Markdown files

Install in one line:

pip install graphify && graphify install

Then type /graphify in Claude Code and point it at anything.

Karpathy asked. Someone delivered in 48 hours.

That is the pace of 2026.

Open Source. Free.

[Boris Cherny @bcherny]

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.

Here goes.

[Eyad @eyad_khrais]

https://t.co/i5L6UIPgH8

[S.C.L @S_C_L_]

https://t.co/Hxl5TXP3ee

[MaxAI @MaxAI_HQ]

@S_C_L_ Firefox extension is on our roadmap. Stay tuned!

[S.C.L @S_C_L_]

@MaxAI_HQ @MaxAI_HQ Can you launch a Firefox extension for the New Year? Thank you!

[Laracasts @laracasts]

I'm happy to announce that we've worked out a deal with @reinink to offer his excellent and massive "Eloquent Performance Patterns" series to all Laracasts subscribers.

The first two episodes are up now, and we'll add more every week until it's complete.

https://t.co/uje6Zqe4fO

[S.C.L @S_C_L_]

剛剛發佈了 1 張相片 https://t.co/QptR3YmwIM

[Shawn Pang @0xshawnpang]

OpenAI的创始人Sam 19岁的他05年成立了位置服务提供商Loopt，12年4300万美元估值被收购，14年上任YCombinator总裁，19年正式上任他和马斯克共同创立的OpenAI，也正是这年他写下了一篇博客 - how to Be Successful / 如何才能成功，整理了一下他的13点分享和我的思考：

[自力6XStudio @hzlzh]

🤖分享我 #ChatGPT 的用法，我把它叫做：垂类小助理，每个助理一个对话框，反复训练它们更懂自己，减少废话和定语，限定回复格式❤️
- 创意助理：从优劣分析我的Idea
- 搜索助理：检索信息来源注明链接
- 代码助理：给出实现思路和代码示例
- 翻译助理：多国翻译同时直出
- 文案助理：错别字和润色文案

[S.C.L @S_C_L_]

剛剛發佈了 1 張相片 @ 漢來蔬食-忠孝店 https://t.co/p7t3kM2psS