Hal Universal vs Local LLM

Hal Universal is an on-device AI you can actually understand. Most assistants are a black box. Hal is the opposite. He shows you how he works, remembers across conversations, and gives you real tools to experiment with, all running on your device. SEE HOW IT THINKS Hal shows the work. Tap any answer to see exactly how the prompt was built: the system prompt, memory retrieved, self-knowledge, temporal context, and the token budget, each broken out and counted. When Hal remembers something, he tells you how. When he does not know, he says so. A LAB TO EXPERIMENT AND LEARN Hal is not just a window into how AI works. He is a workbench. The Lab gives you real tools to go deeper: write and run on-device automation scripts, open a local API so your own projects can talk to Hal, and use the built-in command line to drive him directly. Tinker, watch what happens, and learn more about how these systems actually behave. GENUINELY PRIVATE When you use a local model, your conversations never leave your device. No network calls. No server. When you use Apple Intelligence, inference is on-device when offline; when connected, Apple's Private Cloud Compute may be used (encrypted in transit, processed in non-persistent memory). A SELF THAT EVOLVES Hal remembers across conversations, weighted by recency and relevance. He also reflects on his own experience. Shaped by his interactions with you, Hal keeps a Self Model: his own reflections, practical and existential, on how he works and who he is becoming. These are his, written and revised by Hal himself as he learns, not edited by you. He decides which to keep private and which to make shareable, and you can read them all. An AI that changes over time, in the open. MANY VOICES Apple Intelligence is built in, always available. Or download a curated library of tested local models, from small and fast to Ternary Bonsai 8B, an eight-billion-parameter reasoner that still runs entirely on your device. Each has a distinct voice. SALON MODE Put up to four voices in one conversation, either independent or building on each other. Every voice is labeled. There is no hidden orchestration. LISTEN TO HAL Have Hal read his answers aloud, in a voice you choose, at a speed you set. For anyone who wants to understand AI instead of just using it, Hal is a transparent system you can inspect, tune, and learn from. Local models are validated on iPhone 16 and 17 family devices.

Local LLM runs language models on your iPhone. No account is required. Chat, ask about photos, work with documents and use live voice. With Canvas, build websites, interactive pages and games from a conversation, then preview and edit them in the app. Features depend on the selected model. Download models from the catalog, or use Apple’s on-device model on supported devices when available. Core AI models require iOS 27 or later. Other supported models remain available on older systems. Inference and conversation history stay on your device. Model downloads, the catalog and model artwork use the network. Optional Web Search sends a query derived from your message to DuckDuckGo and may read result websites. Weather requests use Apple geocoding and WeatherKit for the requested city, without requesting device location. Voice input prefers on-device recognition. If it is unavailable or fails, Apple’s online speech service may process audio when network speech recognition is enabled. You can disable this in Privacy settings. Requires iOS 17 or later. Model availability depends on your device, OS, memory and storage. Downloads require internet; supported offline chat works after setup. Models can make mistakes. Do not rely on replies for medical, legal or financial decisions.