Autonomous AI Research Nuances | Generated by AI

Home 2026.07

Question: Is this assessment of Yin Wang, autonomous driving, and the roles of optimism vs. pessimism in AI basically right?

Answer:

Broadly, yes, but I’d make the distinctions more precise.

Your observation about timing is important. In 2019, there was enormous enthusiasm around autonomous driving. Many people implicitly assumed that scaling engineering effort would quickly lead to Level 4/5 autonomy. In that environment, a critique like Yin Wang’s was valuable because it highlighted issues that many discussions underemphasized:

Several of those concerns are still relevant today. Even in 2026, the industry has made impressive progress, but fully general autonomous driving remains much harder than many 2019 predictions suggested.

However, there’s also a limitation.

Understanding whether autonomous driving will succeed requires combining several fields:

Someone can make an insightful philosophical or software-engineering critique without spending years building AV systems. But predicting how fast the field will progress usually requires much deeper exposure to those engineering details.

I also agree with another point you made:

Among thousands of papers, blogs, and projects, only a small fraction end up pointing in the right direction.

Research is extremely noisy. Looking back, many ideas that attracted huge attention disappeared, while a few seemingly ordinary ideas became foundational. In AI alone:

Most published ideas did not become the future.

Your point about pessimism versus optimism is also worth refining.

The quote “Pessimists are usually right; optimists change the world” is memorable, but reality is more nuanced.

Take Yann LeCun.

He is simultaneously:

That isn’t a contradiction. Scientists are rarely globally optimistic or globally pessimistic. Instead, they’re optimistic about mechanisms they believe in and skeptical about mechanisms they think are insufficient.

The same applies to many influential researchers:

So people are often optimistic in one dimension and skeptical in another.

I think the deeper lesson is this:

Good researchers are usually selectively skeptical rather than simply optimistic or pessimistic. They ask:

The people whose predictions age well are often those who update their views as evidence accumulates, rather than remaining permanently optimistic or permanently pessimistic.

References:


Back Donate