Hacker News: ycui7

New comment by ycui7 in "If you are asking for human attention, demonstrate human effort"

ycui7 — Fri, 12 Jun 2026 15:56:32 +0000

At one point, I was thinking that if any of my customer send me a snail mail with an actual physical stamp on it, we will call the customer immediately and solve their problem.

New comment by ycui7 in "New Texas Instruments 5532 chips are not the 5532s we’ve used for decades"

ycui7 — Thu, 04 Jun 2026 00:13:21 +0000

There are better and superior alternative of NE5532 these days. People should just move on. OPA1612 is the king in highest-end audio performance, at least on datasheet paper.

New comment by ycui7 in "Artificial intelligence is not conscious – Ted Chiang"

ycui7 — Thu, 04 Jun 2026 00:01:26 +0000

does it really matter if LLM has conscious? if they produce working code, then it is useful, whoever if they have real conscious of fake intelligence.

we don't know what the conscious in human brain is either.

New comment by ycui7 in "Alphabet announces $80B equity capital raise to expand AI infra and compute"

ycui7 — Mon, 01 Jun 2026 22:06:52 +0000

maybe it is wrong to spend 200B every year continuously to begin with.

New comment by ycui7 in "Alphabet announces $80B equity capital raise to expand AI infra and compute"

ycui7 — Mon, 01 Jun 2026 22:03:20 +0000

so google had spent too much money to build their own datacenter?

New comment by ycui7 in "Green card seekers must leave U.S. to apply, Trump administration says"

ycui7 — Sun, 24 May 2026 00:46:32 +0000

I think what this actually means is that you can apply permanent residency in the US, but you can only get the physical green card outside of the US when the case is approved. So, the last step to get the card need to from outside the country.

New comment by ycui7 in "Apple Silicon costs more than OpenRouter"

ycui7 — Mon, 18 May 2026 00:44:47 +0000

This is not surprising at all. The biggest benefit of cloud model in terms of energy efficiency is that when running more than 1 requests, the power consumption of said GPU roughly stayed the same. The more concurrency requests the server can handle, the less power each request consume. The server GPU is already likely more energy efficient than local GPU, concurrency make the cost structure unbeatable by local hardware. It is generally assumed the local hardware only run 1 request, but if the local engine is meant to serve a small business with meaningful concurrency, the economy might still work out.

New comment by ycui7 in "The Serial TTL connector we deserve"

ycui7 — Sun, 10 May 2026 04:33:04 +0000

Every vendor defines their audio jack connector serial port differently. It is very dangerous to use 3.5mm jack. There is no pinout standard of using 3.5mm.

Even as pure audio jack, the 3.5mm connector has two standards, with the difference on ground and mic.

New comment by ycui7 in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

ycui7 — Sun, 10 May 2026 03:33:23 +0000

The type of people who need spice is dead serious about accuracy. 1ppm error sometimes is not tolerable. So, an optimization in a game engine is definitely not suitable for engineering simulation.

New comment by ycui7 in "A software engineering interview question I like: computing the median"

ycui7 — Tue, 05 May 2026 14:20:02 +0000

if the goal is to only get the median, you should not use sort. sort is O(nlogn). there are algo that give you medium at O(n), check quickselect.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:45:21 +0000

Exiting dGPU for gaming, but staying in the LLM world.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:42:37 +0000

B70 idles at 30W, while RTX PRO 4500 idles at 9W (measured to be 5W at wall).

B70 runs at 1/3 token output rate of RTX PRO 4500 and consume 3X idle power when do nothing.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:37:05 +0000

When you get 4 of these, the idle power alone is 120W. That is a lot of electricity if left on 24/7.

At that power consumption, you also end up being more expensive than API calls and many times slower. It starts to feel very stupid to run local interference.

If the client is very keen on privacy, then they can pay for the NVIDIA.

I end up returning my B70s, and bought RTX PRO 6000.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:31:12 +0000

At this speed, people end up paying more on electricity than api calls. (California electricity)

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:28:59 +0000

You can get 120TPS (144 peak) with Qwen3.6-27B on RTX PRO 6000 with autoround when MTP enabled. It runs faster than sonnet api calls.

5090 gets maybe 100TPS with MTP

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:25:13 +0000

Problem is the more B70 you have, the slower the inference it gets(due to terrible software atm). A single B70 is almost barely faster than CPU inference. If you have 4 B70, you might as well run interference on CPU and be faster with cheaper DDR5 instead of GDDR6.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 03:32:04 +0000

Intel Arc B70 when released, can only produce 1/3 of the token of RTX PRO 4500. Well, it also cost 1/3 of RTX PRO 4500.

It lacked software support the for the primary target application, running LLM. The officially supported vllm fork is 6 version behind mainline. It did not run the latest hot new open models on huggingface. Parallel two of B70 reduce token rate, not improve it. So, the software behind B70 is basically so far behind.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 03:28:40 +0000

It is weird that the reviewer does not mention RTX PRO 6000 96GB, but mentioned RTX PRO 5000 72GB. 72GB RTX PRO 5000 is a special order, and much less people are aware of it. RTX PRO 6000 is known by mostly everyone in the LLM world.

I cannot understand why would a tech reviewer do that.