🤖 Powerful AI empowerment workshop in Macau this week From Cantonese speech recognition to faster administrative approvals and smarter healthcare — the workshop proved that real AI value comes from solving local problems. 💪 Interested in how AI can work for your business in Macau? Let's connect: #AlibabaCloudISV# #AIforMacau# #AInnovation#

🌍Introducing Hy ASR 3.0 preview, a speech recognition model from @TencentHunyuan built to understand, not just transcribe What we improved: - Cleaner on real-world audio: dialects, code-switching, and long-form content with less error accumulation over time - Context-aware correction: homophones and ambiguous phrases get resolved from context, not guessed in isolation - Hotword injection: drop in brand names, people, domain terms without retraining. Lowers integration cost for niche use cases - Built for noisy rooms: whisper, background noise, tricky acoustic conditions stay stable

Students from the UAE built Líng Huà, an Arabic-first Mandarin learning platform powered by Huawei Cloud AI. It removes the need to translate through English, using speech recognition, AI scoring, and translation to help learners develop Mandarin skills intuitively.

We’re growing our Machine Learning Scientist team. At Abridge, we're building the AI platform for the future of healthcare. We started with AI-powered documentation at the point of care. Today, Abridge is integrated into pre- and post-visit, revenue cycle, inpatient care/nursing workflows, clinical decision support, the emergency department, and more. Abridge data is a differentiator. This year alone, Abridge will support 100M+ conversations across 300+ health systems, which means we can train and evaluate models most frontier labs simply can't. That opens up work for LLM post-training, better and more efficient automatic speech recognition, and structured prediction, for starters. We’ve partnered with NVIDIA to build the first foundation model purpose-built for clinical conversations, using Nemotron open models. Our research team is composed of talent from the largest and most experienced AI labs who want to help build a healthcare intelligence platform that is very literally changing how healthcare is delivered at unprecedented scale. Apply today:

One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.

"As We May Think” by Vannevar Bush may be the most prescient piece about technology ever written. He wrote it in 1945 when the word "computer" meant a woman doing arithmetic by hand. It's an essay about how we can use technology to think better. Talks about: – the beginnings of AI – neurotech implants like Neuralink (!!) – the web & hyperlinks – wikipedia – search algorithms – data compression – speech recognition – network routing algorithms – high level programming languages At the time, the transistor had not yet been invented, and there was only one working computer on Earth—Colossus at Bletchley Park—which was classified and nobody knew existed until the 70s.