The improved lengthy context window may even pull data from a number of paperwork when responding to a single immediate. Within the facet panel in Docs, I requested for assist writing a pattern letter to a possible job candidate — within the immediate I linked to the job description doc and the applicant’s PDF portfolio, each of which had been in my Drive — and immediately obtained a electronic mail draft, which factored in related particulars from each paperwork.
Gemini 1.5 Professional isn’t our solely shiny new mannequin, although: I additionally obtained to attempt the freshly-announced Imagen 3, our highest-quality text-to-image mannequin but. One of many new talents I used to be enthusiastic about was its skill to generate ornamental textual content and letters, so I put it via its paces. I began by asking for a stylized alphabet — like letters spelled out in jam on toast, or with silver balloons floating within the sky. Imagen 3 generated a full alphabet of letters, which I may then use to sort out my very own (scrumptious) menus.
After my Imagen 3 interlude, I continued with extra Gemini demos. In one in all them, I may pull up Gemini’s overlay on an Android cellphone and ask questions on something on the display. This actually confirmed how we’re not solely increasing what you may ask Gemini, however we’re additionally making Gemini context conscious, so it may possibly anticipate your wants and supply useful recommendations.
The use case right here was a prolonged oven guide. Whether or not it is a demo or actual life, that is not one thing I might be enthusiastic about studying. As an alternative of skimming via the doc, I pulled up Gemini and instantly obtained an “Ask this PDF” suggestion. I examined questions like “how do I replace the clock” and shortly obtained correct solutions. It labored simply as properly with YouTube movies. As an alternative of watching a 20-minute exercise video, I requested a fast query about easy methods to modify planks, obtained a solution, and was on my method onto the following demo, the place I examined a brand new dialog mode referred to as Gemini Stay that permits you to speak with Gemini within the app, no typing required.
Talking with Gemini was a distinct expertise than the standard chatbot interface: Gemini’s solutions are much more conversational than the paragraphs of texts and bullet-pointed lists you would possibly often get. In my demo, I realized you would even minimize off Gemini in the midst of a solution. After asking for an inventory of child’s actions for a summer time trip, I used to be in a position to interrupt an inventory of recommendations to dive in deeper on what supplies I’d want for tie-dying a shirt.
The Mission Astra — or “superior seeing and speaking responsive agent” — demo took issues a step additional to point out the slicing fringe of the place our conversational AI initiatives are heading.
