Nino
@ninohardt.bsky.social
Marketing scientist, market researcher, choice modeler.
web: ninohardt.com
web: ninohardt.com
Hypothesis: AI enables more rational decision making by consumers.
Evidence, exhibit 1:
Evidence, exhibit 1:
November 17, 2025 at 2:52 PM
Hypothesis: AI enables more rational decision making by consumers.
Evidence, exhibit 1:
Evidence, exhibit 1:
I guess it's either "latest" or "legacy"
November 13, 2025 at 10:40 AM
I guess it's either "latest" or "legacy"
Based on the image, it works
March 19, 2025 at 7:04 PM
Based on the image, it works
PDF support in Gemini is great, but reading numbers off a line chart isn't quite there yet.
March 19, 2025 at 6:57 PM
PDF support in Gemini is great, but reading numbers off a line chart isn't quite there yet.
Say what you want about OpenAI, but its UX doesn't frustrate me the same way as Anthropic Claude.
March 4, 2025 at 11:30 AM
Say what you want about OpenAI, but its UX doesn't frustrate me the same way as Anthropic Claude.
Which is better? 4.5? Seems more elegant.
February 27, 2025 at 9:14 PM
Which is better? 4.5? Seems more elegant.
In written, it works as expected.
January 20, 2025 at 10:01 AM
In written, it works as expected.
Language detection in OpenAI AVM. Why does it recognize my Japanese but then proceeds to speak Spanish?
January 20, 2025 at 9:35 AM
Language detection in OpenAI AVM. Why does it recognize my Japanese but then proceeds to speak Spanish?
Google's AI Studio let's me paste long textual contexts and then engage in a live discussion. OpenAI's AVM doesn't let me do that.
January 19, 2025 at 3:45 PM
Google's AI Studio let's me paste long textual contexts and then engage in a live discussion. OpenAI's AVM doesn't let me do that.
Playing some chess with assistance from Gemini 2.0. Really nice.
December 11, 2024 at 9:27 PM
Playing some chess with assistance from Gemini 2.0. Really nice.
Ok, running it again it beats Nova Pro to it:
December 6, 2024 at 7:10 PM
Ok, running it again it beats Nova Pro to it:
Amazon's Nova Pro passes the strawberry test, it seems.
December 3, 2024 at 10:33 PM
Amazon's Nova Pro passes the strawberry test, it seems.
AI is also good at helping to cut through BS, and we can see Gemini clearly identifies the danger in the fake leadership rules.
December 3, 2024 at 7:36 AM
AI is also good at helping to cut through BS, and we can see Gemini clearly identifies the danger in the fake leadership rules.
Learning from a podcast with Gemini. (1) dropping in the recording, (2) dropping in the transcript (via Deepgram). I am getting similar answers, not sure if it's worth the extra 100k tokens. Thoughts?
December 2, 2024 at 4:42 PM
Learning from a podcast with Gemini. (1) dropping in the recording, (2) dropping in the transcript (via Deepgram). I am getting similar answers, not sure if it's worth the extra 100k tokens. Thoughts?