Skip to content

Commit c93e559

Browse files
committed
Updates
1 parent cf93cf1 commit c93e559

File tree

3 files changed

+19
-2
lines changed

3 files changed

+19
-2
lines changed

_posts/2024-12-08-google-ai-studio.markdown

Lines changed: 19 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,9 +8,9 @@ comments: true
88
published: true
99
---
1010

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.
1212

13-
## Gemini Sample Prompts
13+
## Gemini v1.5 Sample Prompts
1414

1515
Here's an example prompt in the Studio, asking about plantcare based on a photo input.
1616

@@ -27,6 +27,23 @@ After my [tests of OCR a few years ago](/2018/03/06/tabular_ocr_gcv), I found th
2727
<img src="/img/posts/google-ai-studio-santa-claus.png" class="img-fluid" />
2828

2929

30+
## Gemini v2.0 Sample Prompts
31+
32+
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.
35+
36+
<img src="/img/posts/google-ai-studio-plantcare-v2.png" class="img-fluid" />
37+
38+
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:
43+
44+
<img src="/img/posts/google-ai-studio-santa-claus-v2.png" class="img-fluid" />
45+
46+
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.
3047

3148
### More in this series...
3249
* [Google Gemini](/2024/02/16/google-gemini) - Google Gemini
292 KB
Loading
224 KB
Loading

0 commit comments

Comments
 (0)