jlei523 · HackerTrans

há 10 mesesdiscuss

  Intel and AMD have implemented these improvements with Lunar Lake and Strix Halo. You can buy an x86 laptop with Macbook-like efficiency right now if you know which SoCs to pick.

This just isn't true. Yes, Lunar Lake has great idle performance. But if you need to actually use the CPU, it's drastically slower than M4 while consuming more power.

Strix Halo battery life and efficiency is not even in the same ball park.

jlei523

há 10 mesesdiscuss

I think anyone could have seen this from miles away based on:

1. China is going to own the EV market. The only thing that can temporarily stop Chinese EVs from dominating in every country is massive tariffs. But this is not a long-term strategy.

2. Sentiment is low on EV due to Trump

I think the problem with Musk's strategy is that self-driving will also become a commodity over time. There's no reason that only Teslas will be able to drive themselves. Further more, I don't see why China's robotics won't do the same to Tesla's EVs. In fact, I believe China's robotics are world leading at the moment.

jlei523

há 10 mesesdiscuss

"Use DRY coding". 3 words can solve this problem. Maybe put it in the parent prompt.

jlei523

há 10 mesesdiscuss

I disagree with you. You don't need researchers to use your client hardware in order to make inference chips. All big tech are making inference chips in house. AMD and Apple are making local inference do-able on client.

Inference is vastly simpler than training or scientific compute.

jlei523

há 10 mesesdiscuss

  Also I wanted to add that LLMs (at least free ones) are pretty dumb sometimes and do not notice obvious thing. For example, when writing tests they generate lot of duplicated code and do not move it into a helper function, or do not combine tests using parametrization. I have to do it manually every time.

Do you prompt it to reduce duplicated code?

jlei523

há 10 mesesdiscuss

  The new CEO of Intel has said that Intel is giving up competing with Nvidia.

No, he said they're giving up competing against Nvidia in training. Instead, he said Intel will focus on inference.

That's the correct call in my opinion. Training is far more complex and will span multi data centers soon. Intel is too far behind. Inference is much simpler and likely a bigger market going forward.

jlei523

há 7 anosdiscuss

>but high enough that the masses of 1-movie-a-month ordinary users support the 30-movies-a-month power users

How would this work for WeWork though? If someone rents the space, WeWork can't rent it out to someone else. And this is work. People are going to show up on most days - unlike gym memberships.

comments