Services like Delphi are creating functional AI clones of experts (e.g., Michael Ovitz). This allows users to get specialized advice or create novel content, such as a podcast interviewing historical figures like Steve Jobs, moving AI avatars from gimmick to utility.

Until brain-computer interfaces are viable, the highest bandwidth way to interact with AI is through speaking commands (voice out) and receiving information visually (visual in), whether on a screen or via glasses. This is because humans speak significantly faster than they can type.

Brain-computer interfaces that translate thought into text are not yet perfectly accurate. To function effectively, they combine direct neural decoding with computational language models—similar to a phone's autocorrect—which predict likely words and sentences to correct the AI's frequent mistakes.

Designing for users with motor disabilities who control interfaces with their minds presents a unique challenge. Unlike typical design scenarios, it's impossible for designers to truly imagine or simulate the sensory experience, making direct empathy an unreliable tool for closed-loop interactions.

Roblox aims to create personal NPCs by training them on users' specific behaviors, gestures, and speech. These "virtual doppelgangers" could act as agents, performing tasks or standing in for the user in virtual experiences, moving far beyond generic AI companions.

Paradromics uses LLMs to decode brain signals for speech, much like how speech-to-text cleans up audio. This allows for faster, more accurate "thought-to-text" by predicting what a user intends to say, even with imperfect neural data, and correcting errors in real-time.

Due to latency and model uncertainty, a BCI "click" isn't a discrete event. Neuralink designed a continuous visual ramp-up (color, depth, scale) to make the action predictable. This visual feedback allows the user to subconsciously learn and co-adapt their neural inputs, improving the model's accuracy over time.

Neuralink's initial BCI cursor used color to indicate click probability. As users' control improved, the design evolved to a reticle that uses motion and scale for feedback. This change was more effective because the human eye is more sensitive to motion than color, and it better supported advanced interactions.

To help a participant with ALS who couldn't use voice commands to pause the BCI cursor, Neuralink created the "parking spot," a visual gesture-based toggle. This solution, designed for a specific edge case, was immediately adopted by all other participants as a superior, universally valuable feature.