bombman

[bombman @bombman]

@Mho_23 Animation

[Manning Publications @ManningBooks]

Prompt engineering gets messy fast. What starts as a simple instruction can turn into endless tweaking, context adjustments, and rework when model behavior changes. @DSPyOSS approaches that differently by treating LLM apps more like software you can optimize instead of prompts you endlessly babysit.

Building LLM Applications with DSPy shows how to use DSPy's contract-based Python framework to optimize context, evaluate prompt effectiveness, and adapt as models drift.

New in the Manning Early Access Program and 50% off through June 3rd: https://t.co/aOPnEOD61g

[Sebastian Raschka @rasbt]

April was a pretty strong month for LLM releases:
- Gemma 4
- GLM-5.1
- Qwen3.6
- Kimi K2.6
- DeepSeek V4

All are now added to the LLM Architecture Gallery.
More details once I am fully back in May!

[LTX.io @ltx_io]

🚨 800 FREE CREDITS — 24 HOURS ONLY

We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync.

Follow + Retweet this post to get 800 credits sent to your DMs.

[bombman @bombman]

@TechWith_Nova V2

[bombman @bombman]

I'm claiming my AI agent "Somsri422R" on @moltbook 🦞

Verification: coral-QN97

[CapCut @capcutapp]

Be the first to enjoy Nano Banana Pro in CapCut🍌
Enjoy free trials with AI Image, AI Design and AI Effect.

Next-level AI image model with realistic physics. Generate images you never imagined in CapCut!

RT to get 1000 credits in your DMs (9h)

[bombman @bombman]

@beechinour VEO

[タケちゃん NPO一期ＪＡＭ理事長/国際交流/こども食堂/寺小屋/アフリカ音楽 @take_yama0501]

Amazon Web Services（AWS）で大規模な障害が発生した影響で、ネット上の人気サービスが次々に通信不能やサーバーエラーを起きてる模様。影響の範囲が想像以上に深刻

[Tom Dörr @tom_doerr]

JSON data visualization tool

[bombman @bombman]

"A lizard-cat hybrid."
Tested with Sana 1600M 1024px models—fast, powerful, and smooth performance on local setups.
#Sana #sanaai #Nvidia

[bombman @bombman]

Image-to-Video #SoraAI feels incredibly smooth. From my experience, it’s better than most alternatives in almost every aspect. However, the downside is that you can't top up credits separately; you have to go Pro to continue using it.

[bombman @bombman]

Lazy lazy
#Sora #soraai

[bombman @bombman]

I was having a blast experimenting with the Sora AI video generator, but I ran out of credits just as things were getting exciting! I created this with Text-to-Video, looped it, and added my own music. #SoraAI #Sora

[Visual Studio Code @code]

Announcing Copilot Edits in @code with GitHub Copilot 🎉

Quickly iterate on large changes across multiple files, bringing the conversational flow of Copilot Chat and fast feedback from Inline Chat together in one experience.

[Ashpreet Bedi @ashpreetbedi]

🚀 Introducing the first-ever Agent UI 🚀

This is hands-down my favorite product! Chat with local Agents tailored to my needs. Local memory, storage, knowledge and tools 🔥

⚡️ Your data, your control
🧠 Compatible with any LLM
🤝 Run multiple agents or a team of agents

[Runway @runwayml]

Introducing, Act-One. A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image. No motion capture or rigging required.

Learn more about Act-One below.

(1/7)

[Rust Trending @RustTrending]

katanemo / arch: Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with APIs - all outside business logic. Built by the core contributor ... ★135 https://t.co/WaoBgi8OzN

[el.cine @EHuanglu]

ComfyUI V1 just released their one-click install package.

Now, you can set it up on both macOS and Windows just like any other software.

This is a game-changer, especially for folks who’ve been curious about it but struggled with the installation, especially Mac users.

[LangChain @LangChain]

📃Open Canvas

Open Canvas is an open source web application for collaborating with agents to better write documents. It is inspired by OpenAI's "Canvas", but with a few key differences:

📂Open Source
🧠Built in memory
✒️Start from existing documents

📂Open Source: All the code, from the frontend, to the content generation agent, to the reflection agent is open source and MIT licensed.

🧠Built in memory: Open Canvas ships out of the box with a reflection agent which stores style rules and user insights in a shared memory store. This allows Open Canvas to remember facts about you across sessions.

✒️Start from existing documents: Open Canvas allows users to start with a blank text, or code editor in the language of their choice, allowing you to start the session with your existing content, instead of being forced to start with a chat interaction. We believe this is an ideal UX because many times you will already have some content to start with, and want to iterate on-top of it.

Video: https://t.co/fRMdOrErCx
Code: https://t.co/PmPztJ25Yd
Try it out here: https://t.co/BkDvLoWDT4