#On-device

AIA Chinese podcast transcript argues that Opus 5.5 makes code generation, game modding, and language migration much faster and cheaper. It cites examples such as game remakes, Photoshop clones, and ESP32 firmware projects, and says legal and open-source barriers are struggling to keep pace.

AILiquid AI is building personal AI that runs on devices such as phones, wearables, PCs, and cars, using its Liquid Context layer, which is optimized for Snapdragon processors, to sit between models, agents, and hardware. The company's agent harness uses its own models to decide which user context to retain and how to compress it within fixed compute limits. Liquid AI is also collaborating with Mercedes-Benz Group AG to bring on-device AI to its cars and plans observability and continuous improvement loops for self-improving agents.

AIHarrison Chase, founder of LangChain, endorsed a post on harnesses with the brief comment "Good take on harnesses." The post, from @zeeg, argues that general coding harnesses like Codex will be superseded by specialized ones and that local models will handle most daily tasks within five years.

AIThe author reports that a dual RTX 5070 Ti setup running Qwen Flash rose from 200 prefill and 10 decode to 2200 prefill and 67 decode, now on a single card, using Strata and a custom PR. The post argues that such consumer-hardware speeds, once limited to top-end machines, could pressure the economics of selling model compute via API.

AIThomas Wolf says most personal AI should run on users' devices and praises Sigil's Underdog, which is powered by the Hugging Face Hub. Underdog's announcement says it aims to deliver free, private AI that runs on consumer hardware, with backing from a16z, Khosla Ventures, and other investors.

AIGoogle Cloud argues startups should combine open-weight models with frontier APIs rather than routing every request to one frontier model. It cites Gemma 4, which spans five sizes including a 31B dense model and a 26B A4B Mixture-of-Experts model, released under Apache 2.0. The article's examples report a 44% latency drop for Cue, from 876 ms to 488 ms, and a $0 server cost for BetterSpeak's on-device Gemma 4 E2B.

AILiquid AI's post-training team, including Maxime Labonne, Edoardo Mosca, and Jiahui Wang, discusses what makes an on-device agentic model useful. The post says post-training shapes how models learn to use tools, follow instructions, handle longer contexts, and recover when tasks become complex.

AIKDE's Akademy conference in Graz, Austria, opens on September 19, where contributors Eva Brucherseifer and Jan Muehlig will present a talk proposing an "AI-native" KDE desktop built on a personal, encrypted "Kadai" kernel. The proposal's middle section is expected to divide attendees, while the project marks its 30th anniversary, with KDE 1.0 released in July 1998.

AIGeorgi Gerganov says Computex this year shows a strong signal for local AI, with major players like NVIDIA and Microsoft embracing and discussing local AI workloads. He adds that dedicated consumer hardware and models are on the way.