Very useful tips on tool use and memory from Manus's context engineering blog post. Key takeaways. 1. Reversible compact summary Most models allow 128K context, which can easily fill up after a few turns when working with data like PDFs or web pages. When the context gets full, they have to compact it. It’s important to compact the context so that it’s reversible. Eg, removing the content of a file/web page if the path/URL is kept.
GENERATIVE AI
-
Free LLM Tool Available Now at Datasette
By
–
I'm currently giving it away for free https://
llm.datasette.io -
GitHub Spark: AI-powered React app platform with auth and storage
By
–
GitHub released Spark yesterday, their extremely well crafted prompt-to-app platform for creating and iterating on React apps with user auth and persistent storage I like it a lot! I reverse engineered it with Spark itself, the details are fascinating
-
Non-Developer Empowerment: Building Software Without Coding Skills
By
–
I pay for lovable. have built a handful of internal tools and gotten value, but even moreso I love being a non-dev and yet I can make software. After years of being told "no" by the devs at work (back before I started my own business) I can finally say Yes to everything
-
Hailuo AI 02 Video Generation Model Access and Creative Experiments
By
–
🔥 ¡NUEVO VÍDEO en el LAB! 🔥
— Carlos Santana (@DotCSV) 24 juillet 2025
Hoy los amigos de Hailuo AI me han dado acceso ilimitado a su modelo Hailuo 02, uno de los modelos de generación de vídeo más potente, sobre todo simulando físicas, y con él vamos a jugar!
Abrochaos los cinturones, que se viene vídeo bien fresco 🌊 pic.twitter.com/sLyEFMPNgJ¡NUEVO VÍDEO en el LAB! Hoy los amigos de Hailuo AI me han dado acceso ilimitado a su modelo Hailuo 02, uno de los modelos de generación de vídeo más potente, sobre todo simulando físicas, y con él vamos a jugar! Abrochaos los cinturones, que se viene vídeo bien fresco
-
Claude Sonnet 4 Custom Prompt Project Implementation
By
–
Claude Sonnet 4 with a custom prompt in a project
-
Kimi K2: Open-Source Trillion-Parameter MoE Model Released
By
–
Kimi K2 = Hype or Not?
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 24 juillet 2025
It is the first open‑source trillion‑parameter MoE model
• 1 T total / 32 B active parameters → giant yet efficient
• Outscores GPT‑4.1 & Claude‑4 (65.8 % SWE‑Bench, 53.7 % LiveCodeBench)
• 128 k context, MIT‑licensed, no vision implemented…… pic.twitter.com/tiouZDLCScKimi K2 = Hype or Not? It is the first open‑source trillion‑parameter MoE model • 1 T total / 32 B active parameters → giant yet efficient
• Outscores GPT‑4.1 & Claude‑4 (65.8 % SWE‑Bench, 53.7 % LiveCodeBench)
• 128 k context, MIT‑licensed, no vision implemented… -
AI Not Yet Main Cause of Youth Hiring Slowdown
By
–
There is a slowdown in hiring young people in both the US and UK, but the evidence continues to suggest that the cause is generally not AI (at least not yet)
-
Gemini 2.5 Pro Achieves Gold-Winning IMO Performance
By
–
Gemini 2.5 Pro Capable of Winning Gold at IMO 2025 Yichen Huang, Lin F. Yang: https://
arxiv.org/abs/2507.15855
v2
… #ArtificialIntelligence #DeepLearning #MachineLearning -
Ultra3D: Efficient High-Fidelity 3D Generation with Part Attention
By
–
Ultra3D Efficient and High-Fidelity 3D Generation with Part Attention