#on-device inference
185 related articles
·2 min
Gemini 3.5 Pro's Repeated Delays: The Real Logic Behind the LLM Race
Gemini 3.5 Pro's latest delay sparks community debate. This article dives deep into the technical causes, safety review pressures, and expectation-management challenges behind frequent LLM delays.
Read more →
·4 min
Complete Guide to Gesture Control on Huawei Sound X5: From Waving to Switch Songs to Whole-Home Automation
The Huawei Sound X5 is more than a Bluetooth speaker! Learn how to activate wave detection via the Smart Life App for contactless song switching, volume control, AC control, and whole-home automation.
Read more →
·7 min
GPT-5.6 and Grok 4.5 Launch Simultaneously, Meta Unveils Agent-Based Image Model
OpenAI GPT-5.6 expands its preview, xAI Grok 4.5 opens access at the same time, Meta releases the Agent-based Muse Image model and Muse Video model, while Apple and DeepSeek launch in-house AI inference chip programs. A quick look at the week's five biggest AI stories.
Read more →
·2 min
WisprGemma: Fully Local In-Browser Voice Input — Your Audio Never Leaves Your Device
WisprGemma is an open-source, browser-local voice input tool built on WebGPU and Transformers.js. One Gemma model handles speech recognition and text polish — your voice never leaves your device.
Read more →
Apple Sues OpenAI Over Trade Secret Th…
·5 min
Apple Sues OpenAI Over Trade Secret Theft: The Deep Logic Behind a Broken Coopetition
Apple has filed a trade secret lawsuit against OpenAI, fracturing the once-deep partnership between the two tech giants. A deep analysis of talent mobility, tech competition, and AI coopetition.
Read more →
·7 min
Rumored Pixel-Wide Price Hike: Watch 5 Starting Price May Rise to $399
Per French leak site Dealabs, Google's Pixel lineup may see across-the-board price hikes. The Pixel Watch 5 41mm could start at $399, with the LTE version reaching $499—nearly 15% higher than the Watch 4.
Read more →
·2 min
MOSS-Transcribe-Diarize: A 0.9B End-to-End Multi-Speaker Speech Transcription Model
MosiAI open-sources MOSS-Transcribe-Diarize-0.9B: unified speech transcription and speaker diarization, 128K context for 90-min audio, hotword boosting, SGLang Day-0 support, edge-deployable.
Read more →
·6 min
GPT-5.6 Now Widely Available: The Era of Three-Tier Models and Multi-Agent Orchestration Arrives
OpenAI releases GPT-5.6 (SOUL/TERRA/LUNA), with Ultra mode running four agents in parallel; Meta launches Muse Spark 1.1 with million-token context; ChatGPT desktop unifies Chat, Work, and Codex.
Read more →
·7 min
Gemini Live Integrates Nano Banana: A Complete Guide to Real-Time Camera, Image Generation, and Maps Integration
Google's Gemini Live now integrates the Nano Banana image generation model with Connected Apps like Google Maps, supporting real-time camera scene understanding and visualization. Free worldwide.
Read more →
·5 min
Has Apple Lost the AI Race? The Battle Between Software Setbacks and the Hardware Moat
After Apple failed to deliver on its new Siri promise for two years running, many ask: has Apple lost the AI race? We break down two AI tracks—software models vs. on-device hardware.
Read more →
·3 min
Claude's 'Usage Reflection' Feature: How AI Can Help You Examine Your Own Habits
Anthropic launches 'Usage Reflection' for Claude, helping users examine AI interaction patterns and identify over-reliance risks. A look at the product logic, privacy considerations, and why AI literacy matters.
Read more →
·2 min
Gemini Personalized Image Generation: Connecting the Google Ecosystem So AI Truly "Gets You"
Google opens Gemini's personalized image generation to more U.S. users for free, connecting Gmail, Photos, and Calendar data to let AI understand your preferences and generate contextually relevant images.
Read more →
·3 min
Running LLMs Locally: The Illusion vs. the Real Value of Open-Weight Models
Open weight ≠ runnable locally. This article breaks down the hardware barriers, VRAM limits, electricity costs, and parallelism constraints of models like GLM 5.2 and DeepSeek — revealing where open-weight models truly add value: driving cloud competition, not home replication.
Read more →
·3 min
GPT-5.6 Three-Tier Model Lineup Leaked, OpenAI May Delay IPO to Next Year
OpenAI previews GPT-5.6 models Sol, Terra, Luna; Codex launches on mobile; SenseTime develops U1 Pro rivaling GPT Image; Gemini enters Android Auto; OpenAI IPO may slip to next year.
Read more →
·3 min
GPT-5.6 Three-Model Launch, SenseNova Open-Source Training Stack: A Day of Dense AI Industry Updates
OpenAI launches GPT-5.6 Sol/Terra/Luna, SenseNova open-sources its full multimodal training stack, Gemini adds free Study Notebooks, Apple M7 brings on-device AI to mainstream — a roundup of today's AI updates.
Read more →
·6 min
Xiaomi XiaoAI 10.1-inch Smart Control Panel: Is the AI LLM Integration Worth It?
Xiaomi XiaoAI 10.1-inch Smart Control Panel features AI LLM Q&A, WeChat calling, and whole-home Mi IoT control. Priced at 839 yuan, ~679 yuan after national subsidy. An in-depth review of AI capabilities, screen experience, and smart home integration.
Read more →
·6 min
Made by Google Event Confirmed: New Pixel Phones with AI Capabilities Coming Soon
Google confirms the Made by Google hardware event in NYC, unveiling next-gen Pixel phones with new Tensor chips and deep Gemini AI integration. On-device AI gets a major upgrade.
Read more →
Google Drops Two New Models: 4-Second …
·4 min
Google Drops Two New Models: 4-Second Image Generation + Real-Time Video Creation Explained
Google launches Imagen 3 Nano (Flash) for 4-second text-to-image generation and Veo 3 Flash for conversational video editing — now available via Gemini API and Google AI Studio.
Read more →
·5 min
Five Major Gemini Spark Upgrades: Building an Around-the-Clock Proactive Personal AI Agent
Google launches five major Gemini Spark upgrades including macOS native integration and Smart Triggers, transforming AI assistants from passive chat tools into proactive Personal AI Agents for around-the-clock autonomous task handling.
Read more →
·5 min
Five Major Upgrades to Gemini Spark: Building an Always-On Proactive Personal AI Agent
Google launches five major Gemini Spark upgrades including macOS native integration and Smart Triggers, transforming AI from passive chatbot to proactive Personal AI Agent for always-on task handling.
Read more →