You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: _posts/2024-12-08-google-ai-studio.markdown
+19-2Lines changed: 19 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,9 +8,9 @@ comments: true
8
8
published: true
9
9
---
10
10
11
-
After I completed a [5-day course](https://rsvp.withgoogle.com/events/google-generative-ai-intensive) last month covering Google's current AI offerings, I wanted to play around in the [Google AI Studio](https://aistudio.google.com/) a bit more. In particular, I wanted to check out the Gemini LLM via some prompts.
11
+
After I completed a [5-day course](https://rsvp.withgoogle.com/events/google-generative-ai-intensive) last month covering Google's current AI offerings, I wanted to play around in the [Google AI Studio](https://aistudio.google.com/) a bit more. In particular, I wanted to check out the Gemini LLM via some prompts. Initially, I used the Gemini v1.5 Flash model.
12
12
13
-
## Gemini Sample Prompts
13
+
## Gemini v1.5 Sample Prompts
14
14
15
15
Here's an example prompt in the Studio, asking about plantcare based on a photo input.
16
16
@@ -27,6 +27,23 @@ After my [tests of OCR a few years ago](/2018/03/06/tabular_ocr_gcv), I found th
A few days after I posted above using Gemini v1.5, Google [annouced Gemini v2.0](https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024) and made it available to test within Google AI Studio. So, I went back and tried out the same sample prompts.
33
+
34
+
Interestingly, using the Gemini 2.0 Flash experimental model, providing the same input photo and prompt as before.
I was told it was a different plant than Gemini v1.5 labelled. As I am not a botanist or florist, I actually don't know which (if either) model labelling is correct. This is a good example of non-experts being convinced of LLM output, even when it may be plain wrong.
39
+
40
+
Gemini v1.5 and v2.0 both handled the structured output task for trip recommendations nearly identically.
41
+
42
+
The letter from Santa to Emma, seemed to have a little more *heart* using the Gemini v2.0 model:
P.S. For those interested, the 5-day course I took is now available as a [Learning Guide](https://www.kaggle.com/learn-guide/5-day-genai) so don't feel left out if you missed it first time.
30
47
31
48
### More in this series...
32
49
*[Google Gemini](/2024/02/16/google-gemini) - Google Gemini
0 commit comments