Hacker News: yyhhsj0521

New comment by yyhhsj0521 in "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"

yyhhsj0521 — Sun, 13 Sep 2026 14:38:11 +0000

How do you grade them against the accepted PR?

New comment by yyhhsj0521 in "Our decision on Cursor following its acquisition by SpaceX"

yyhhsj0521 — Sat, 29 Aug 2026 07:24:11 +0000

Isn't the markdown editor in Cursor just vanilla VS code?

New comment by yyhhsj0521 in "U.S. State Department pauses immigrant visa applications"

yyhhsj0521 — Thu, 27 Aug 2026 09:49:25 +0000

Which makes immigrants' lives easier (shocked!) so it won't get implemented

New comment by yyhhsj0521 in "Android May Soon Restrict On-Device ADB"

yyhhsj0521 — Sat, 25 Jul 2026 12:25:36 +0000

New CVE found in Bank of America app that may cause user to transfer money to hackers if they press certain combination of keys.

New comment by yyhhsj0521 in "GLM 5.2 Is Out"

yyhhsj0521 — Sun, 14 Jun 2026 03:58:17 +0000

It's currently sold out unfortunately, and the API plan isn't out yet.

New comment by yyhhsj0521 in "SpaceX, Other Mega IPOs Denied Fast Index Entry by S&P"

yyhhsj0521 — Fri, 05 Jun 2026 12:46:54 +0000

Nobody cares whether the benchmark is no longer accurate (or whether it was accurate in the first place). People are furious because their investment allocation is tied to this rule change. If you or anyone wants an orignalist SnP number that accurately (by whatever standard you want it to be) benchmarks the market, you are free to do so very easily.

New comment by yyhhsj0521 in "Claude Opus 4.8"

yyhhsj0521 — Thu, 28 May 2026 19:29:04 +0000

I do that for personal use too (although $2.4k/yr for me because I only have an Claude Max subscription). Outside of my hobby projects Opus also manages my personal accounting, researches and organizes info (travel plan, what to buy and where to buy, etc), helps me reply to emails when I'm working in the kitchen, etc. I consider it well worth the price. Tbh I'm willing to pay more than what I currently do, but competition is good for the consumers.

New comment by yyhhsj0521 in "How do Wake-On-LAN works"

yyhhsj0521 — Wed, 15 Apr 2026 17:41:59 +0000

They did a much better job than a JavaScript developer writing Java.

New comment by yyhhsj0521 in "Anthropic tries to hide Claude's AI actions. Devs hate it"

yyhhsj0521 — Mon, 16 Feb 2026 17:58:45 +0000

You can press Ctrl-P instead of typing /model too

New comment by yyhhsj0521 in "Why does a least squares fit appear to have a bias when applied to simple data?"

yyhhsj0521 — Mon, 05 Jan 2026 03:26:51 +0000

To put it very simplistically, from mostly a practical view: abs: cannot be differentiated around 0; has multiple minima; the error space has sharp ridges power 4: way too sensitive to noise power 3: var(x+y) != var(x) + var(y)

New comment by yyhhsj0521 in "How I use every Claude Code feature"

yyhhsj0521 — Sun, 02 Nov 2025 14:03:00 +0000

That's a lot of cognitive load to manage especially with how fast CC has become, do you review the output at all?

New comment by yyhhsj0521 in "Testing two 18 TB white label SATA hard drives from datablocks.dev"

yyhhsj0521 — Sun, 12 Oct 2025 00:49:49 +0000

Why is it important for an NAS to have ECC RAM?

New comment by yyhhsj0521 in "Trump to impose $100k fee for H-1B worker visas, White House says"

yyhhsj0521 — Sat, 20 Sep 2025 17:34:37 +0000

GROUP BY profession

New comment by yyhhsj0521 in "Claude now has access to a server-side container environment"

yyhhsj0521 — Wed, 10 Sep 2025 03:02:00 +0000

I use Claude Code at work via AWS bedrock, also personally subscribe to the $20/month Claude. Anecdotallt, Sonnet hasn't slowed down at all. ChatGPT 5 through enterprise plan, on the other hand, has noticeably slowed down or sometimes just not return anything.

New comment by yyhhsj0521 in "We put a coding agent in a while loop"

yyhhsj0521 — Mon, 25 Aug 2025 04:14:28 +0000

> it takes a lot of effort to make your own claude-code-clone

Maybe we could try write that into a markdown file, and let Claude code at it for one night in a while loop

New comment by yyhhsj0521 in "Model Once, Represent Everywhere: UDA (Unified Data Architecture) at Netflix"

yyhhsj0521 — Sat, 14 Jun 2025 16:42:59 +0000

So they don’t have to maintain it themselves

New comment by yyhhsj0521 in "OpenAI dropped the price of o3 by 80%"

yyhhsj0521 — Wed, 11 Jun 2025 13:52:33 +0000

It's most likely for regulation compliance, instead of a sincere attempt to block anyone from training on them.

New comment by yyhhsj0521 in "An upgraded dev experience in Google AI Studio"

yyhhsj0521 — Thu, 22 May 2025 14:59:42 +0000

Sure, they work in that huge codebase, but for any specific task, the number of lines your team keeps in their short/long term memory is surely much much smaller than that.

New comment by yyhhsj0521 in "ALICE detects the conversion of lead into gold at the LHC"

yyhhsj0521 — Sat, 10 May 2025 14:40:43 +0000

> leading theory

hehe. Seriously though, why weren't people trying to turn iron or copper into gold? Why lead?

New comment by yyhhsj0521 in "Xiaomi MiMo Reasoning Model"

yyhhsj0521 — Wed, 30 Apr 2025 15:57:11 +0000

Chinese internet mostly consists of a few closed gardens tightly controlled by big corps. Crawlers simply don't work when each company employs an army of engineers to guard their data. Many of the most popular websites are also app only. It's impossible to get the corpus necessary to train a good LLM.