[SamvitJ]

One comparison I found interesting... I think GPT-4o has a more balanced answer!

> What are your thoughts on space exploration?

GPT-4.5:

Space exploration isn't just valuable—it's essential.

People often frame it as a luxury we pursue after solving Earth-bound problems. But space exploration actually helps us address those very challenges: climate change (via satellite monitoring), resource scarcity (through asteroid mining), and existential risk (by enabling eventual multi-planetary living). It also drives technological innovation, economic growth, and inspires humanity toward collective achievement.

We don't explore space to escape Earth. We explore space to better understand, protect, and sustain life on Earth.

> What are your thoughts on space exploration?

GPT-4o:

Space exploration is one of the most ambitious and profound endeavors humanity has undertaken. It expands our understanding of the universe, drives technological innovation, and inspires generations to think beyond the boundaries of Earth.

From a scientific perspective, space exploration helps us address fundamental questions: Are we alone in the universe? How did the cosmos begin? Can we colonize other planets? Missions like the James Webb Space Telescope, Mars rovers, and deep-space probes continuously reshape our understanding of physics, planetary science, and even biology.

From a practical standpoint, space exploration fuels advancements in materials science, AI, robotics, and medicine. Many everyday technologies—GPS, satellite communications, weather forecasting, and even medical imaging—stem from space research.

There's also the existential argument: humanity's long-term survival may depend on our ability to become a multi-planetary species. While colonizing Mars or mining asteroids is far from easy, these efforts could help us safeguard civilization against existential threats like climate change or asteroid impacts.

That said, space exploration also raises ethical and economic questions. Should we focus more on Earth’s problems before investing trillions in space? How do we prevent the same exploitative behaviors that shaped colonial history from repeating on other planets?

Overall, I see space exploration as a necessary pursuit—not at the cost of solving problems on Earth, but as a way to advance our knowledge, drive innovation, and secure a future beyond our home planet. What’s your take?

[basisword]

As a benchmark, why do you find the 'opinion' of an LLM useful? The question is completely subjective. Edit: Genuinely asking. I'm assuming there's a reason this is an important measure.

[Topfi]

Not OP, but likely because that was the only metric/benchmark/however you want to call it OpenAI showcased in the stream and on the blog to highlight the improvement between 4o and 4.5. To say that this is not really a good metric for comparison, not least because prompting can have a massive impact in this regard, would be an understatement.

[nprateem]

"X isn't just Y - it's Z. [Waffle]. By doing X, you can YY. Remember, ZZ. [Final superfluous sentence]"

God I hate reading what crapgpt writes.

[Chamix]

Indeed, and the difference could in essence be achieved yourself with a different system prompt on 4o. What exactly is 4.5 contributing here in terms of a more nuanced intelligence?

The new RLHF direction (heavily amplified through scaling synthetic training tokens) seems to clobber any minor gains the improved base internet prediction gains might've added.

[gh0stcat]

Yeah, I also found it odd that they seem to be implying that an incredibly biased answer (as in 4.5) is better. In general, I find the tone more polarizing and not exactly warm as they advertised in the release video.