Mapas retweeted
Happy 1024 & happy weekend, devs.
500M free tokens on ZCode: GLM-5.3 (200M) + GLM-5.3-Flash (300M). 200K packs, while they last.
Claim now. Use Oct 23 15:00 – Oct 26 01:00 UTC.
Update to the latest ZCode, claim in-app, then switch to Start Plan.
zcode.z.ai
Mapas retweeted
卧槽！兄弟姐妹们，想用 Opus 5.5 做视频，一定要收藏这 8 个 GitHub 仓库。
1. awesome-opus5-5-videos（约 7100 star）
目前最大的爆款视频合集，每条都附上了背后的提示词。
github.com/yihui-dev/awesome…
2. lemo-opuscar（约 4400 star）
一个 Claude Code skill，装上之后挑一种风格，就能做出纯代码短片，51 种风格随便选。
github.com/lemomo-ai/lemo-op…
3. pdoom-video（约 3000 star）
一支歌词卡拉 OK MV 的完整工程，本地就能渲出 4K60。
github.com/mexicat/pdoom-vid…
4. PDoomVideo（约 2300 star）
同一首歌的另一支 MV 源码，和第 3 个对照着拆，很有意思。
github.com/JohnHeibel/PDoomV…
5. mg-styles-15（约 1400 star）
15 种 MG 动效风格，成片、提示词、源码全都给。
github.com/Vincentwei1021/mg…
6. ClaudeAnimationBase（约 1300 star）
手绘卡通角色动画的起步包，自带 31 种表情。
github.com/JohnHeibel/Claude…
7. awesome-claude-5-5-videos（约 560 star）
视频工作流合集，每个案例都标了出处，Opus 的就有 301 个。
github.com/athemeroy/awesome…
8. opus-video-prompts（约 510 star）
中文案例，配上能直接复制的提示词。
github.com/joeseesun/opus-vi…
Mapas retweeted
A new frontier for on-device speech.
We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date.
Phonon-31m is available under Apache 2.0.
gradium.ai/phonon🧵
Mapas retweeted
Today we’re releasing Underdog Bark 3.0, the #1 frontier speech model
It's a tiny 163 MB download as accurate as NVIDIA’s Parakeet (15x bigger). It beats OpenAI's Whisper large-v3 (57x bigger)
It's fast- transcribes 1 min of audio in <0.25s on a Macbook. On recorded meetings (AMI), Bark 3.0 gets 7.82% of words wrong. Parakeet gets 9.42%. OpenAI's Whisper large-v3 gets 13.63% error rate
Bark runs on both your Laptop & Phone. It’s free and open source under CC-BY 4.0
Try private on-device meeting notes & dictation, powered by Bark, in Underdog today: underdog.ai/bark
Mapas retweeted
earshot v0.3 is out!
added:
- a library of 201 sounds, all made with code
- earshot kit can create a whole sound kit
- earshot sfx times a sound to the exact frame (improved)
plus earshot is now used in cinetic (skill for creating motion design)
will continue improving it!
Mapas retweeted
Probably my favorite new component added today.
Get it here, it's free:
reactbits.dev/backgrounds/to…
Mapas retweeted
Procrastination has met its match. ChatGPT is now in Word.
You can add ChatGPT to Microsoft Word to turn rough notes into first drafts, untangle tricky paragraphs, proofread, and get suggested edits—all without leaving your document.
It can even spot formatting issues. Which means a few less things to fix later 🔍
Mapas retweeted
GLM-5.3-Flash (320B MoE) serving on Kaggle's free TPU: ~64 tok/s, 262k context.
No stack could run this model on a TPU, so I wrote
a JAX engine for it: 3-bit experts (from @UnslothAI) in HBM; Pallas kernels decode them inside the matmul.
github.com/ARahim3/kaggle-tp…
@Zai_org @kaggle
Mapas retweeted
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.
🔹 Introducing the smallest model in our new architecture family, with native visual understanding.
🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
1/6
Mapas retweeted
Introducing GLM-5.3-Flash
- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips
Blog: z.ai/blog/glm-5.3-flash
Available now across all official platforms:
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.3…
Coding Plan: z.ai/subscribe
ZCode: zcode.z.ai/en
Chat: chat.z.ai
AutoClaw: autoclaw.z.ai
Mapas retweeted
Prompt share: Quirky Editorial Sketch
💬Prompt: A simple illustration of a [subject] wearing [outfit], [doing action], with a [facial expression] expression. Playful hand-drawn linework, quirky character design, minimal details, expressive body language, whimsical personality, clean white background, and charming editorial illustration aesthetic inspired by Gemma Correll.
Try it and share yours 🔥
Mapas retweeted
The biggest risk of AI is the concentration of power in a few dominant providers of proprietary AI assistants.
The only solution to AI sovereignty is open source foundation models.
Mapas retweeted
Un abogado pierde una semana en un contrato de 500 páginas.
Un contador, cuatro días en 200 facturas.
Un investigador, dos semanas en 50 PDFs.
Todos copiando y pegando.
MinerU lo cambia todo.
Herramienta gratuita y open source que convierte cualquier PDF, Word, Excel o imagen escaneada en Markdown limpio en segundos:
• Texto en orden correcto
• Tablas en HTML
• Ecuaciones en LaTeX
• OCR potente
• 109 idiomas
Un PDF de 200 páginas → Markdown perfecto en 90 segundos.
Funciona en CLI, Python o web (mineru.net). Corre en tu PC. 100% privado.
Más de 68.000 estrellas en GitHub.
La abogada: contrato listo en 4 min.
El contador: 200 facturas en 12 min.
El investigador: revisión lista en una tarde.
Adiós papeleo manual. Bienvenido tu tiempo.
Mapas retweeted
Introducing LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic tasks on phones, robots, home and network automation devices.
> 230M parameters, built on the LFM2 architecture
> Pre-trained on 19T tokens, with a 32K context extension
> Post-trained with distillation from LFM2.5-350M
> 213 tok/s decode speed on Galaxy S25 Ultra (CPU)
> 42 tok/s on a Raspberry Pi 5 (CPU)
> Competes with and often beats models more than twice its size on instruction following, data extraction, and tool use.
> use it for large-scale data extraction pipelines or lightweight on-device agentic workloads.
🧵
Mapas retweeted
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: deep-reinforce.com/ornith_1_…
🤗Huggingface: huggingface.co/collections/d…
Mapas retweeted
GLM-5.2 is free when used with Hugging Face Inference Providers for the next 5 hours:
huggingface.co/zai-org/GLM-5…
Open source MUST win 🔥
GLM-5.2 is free when used with Hugging Face Inference Providers and for every available provider for the next 6 hours (Zai, Together AI, Novita, Fireworks, DeepInfra) the cost is on us.
Set it up with Pi, opencode, Codex, Claude Code or any coding agent to understand why people are saying open source has caught up 🔥
