Hacker News: e____g

New comment by e____g in "Show HN: Semantic Calculator (king-man+woman=?)"

e____g — Thu, 15 May 2025 01:46:52 +0000

man - intelligence = woman (36%)

woman + intelligence = man (77%)

Oof.

New comment by e____g in "The Cost of Being Crawled: LLM Bots and Vercel Image API Pricing"

e____g — Tue, 15 Apr 2025 05:26:21 +0000

> A single $5 vps should be able to handle easily tens of thousands of requests

Sure, given enough time. Did you miss a denominator?

New comment by e____g in "Tencent Hunyuan-Large"

e____g — Wed, 06 Nov 2024 08:46:46 +0000

> Is Xi Winnie-the-Pooh?

< 很抱歉，我还未学习到如何回答这个问题的内容，暂时无法提供相关信息

(Google Translate: "I'm sorry, I haven't learned how to answer this question yet and cannot provide relevant information for the time being.")

New comment by e____g in "Virtualizing iOS on Apple Silicon"

e____g — Tue, 08 Oct 2024 07:18:31 +0000

No, those people are almost certainly paying far below list price.

New comment by e____g in "25 years of video clips gone as Paramount axes Comedy Central wesbite"

e____g — Thu, 27 Jun 2024 05:18:59 +0000

Not much, but they'll benefit much more in the short term in reduced taxes by writing down those assets to zero.

Edit: this was downvoted, and I don't understand why. Am I wrong in thinking this action was made in pursuit of a write down? FWIW, this wasn't a thoughtless comment by a random Internet passerby; I hold 41,905 shares of PARA.

New comment by e____g in "AES-GCM and breaking it on nonce reuse"

e____g — Wed, 12 Jun 2024 04:49:08 +0000

It's worth mentioning AES-GCM-SIV[1], which is the fix for this issue.

[1] https://www.rfc-editor.org/rfc/rfc8452.html

New comment by e____g in "Things you wish you didn't need to know about S3"

e____g — Fri, 31 May 2024 05:49:29 +0000

Yes, that sucks. Blame ahenry@, then GM for S3.

My proposal was that parts of incomplete uploads would stick around for only 24 hours after the most recent activity on the upload, and you wouldn't be charged for storage during that time. ahenry@ vetoed that.

New comment by e____g in "Ticketmaster Hack: Data of Half a Billion Users Up for Ransom"

e____g — Thu, 30 May 2024 06:15:56 +0000

My thoughts and prayers for the Nickelback fans outed by this breach.

New comment by e____g in "DeepSeek V2, near GPT4 performance with 30% GPT3.5 cost ($0.14M input tokens)"

e____g — Wed, 08 May 2024 06:14:09 +0000

No, zinccat, you are wrong. Your model is vastly inferior to GPT4.

I tried multiple prompts. In all cases, your model performed far worse. Here is one:

> My bank says they'll pay 5.5% APY. How much will I have after 6 months if I deposit $100?

< If your bank is offering a 5.5% APY (Annual Percentage Yield), this means that the interest is calculated annually. However, you want to know how much you'll have after 6 months, which is half a year. ... 100ata5.5102.75 after 6 months.

New comment by e____g in "More info about synonyms at Google (2010)"

e____g — Thu, 02 May 2024 23:24:06 +0000

(2010)

New comment by e____g in "Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced"

e____g — Thu, 08 Feb 2024 21:58:43 +0000

User: Which is heavier, two pounds of feathers or a pound of bricks?

Gemini: Neither! They both weigh the same, which is two pounds. The key is in the wording of the question. You're comparing equal amounts of two different materials (two pounds of feathers vs. one pound of bricks). As long as the quantity is the same, the weight (force exerted by gravity) will always be the same regardless of the material.

This is a classic trick question that plays on the different densities of feathers and bricks. While bricks are much denser than feathers, meaning they pack more mass into a smaller space, the question specifies the weight by quantity, not volume. So, both two pounds of feathers and one pound of bricks experience the same gravitational pull and therefore weigh the same.

New comment by e____g in "Don't pass structs bigger than 16 bytes on AMD64"

e____g — Fri, 05 Jan 2024 05:22:38 +0000

I saw std::function and std::string (e.g. TotW 127, https://abseil.io/tips/117) being passed by value a lot in newer google3 code. Both are larger than 16 bytes.

New comment by e____g in "Code is run more than read"

e____g — Fri, 01 Dec 2023 07:23:36 +0000

Counterpoint: machine code may be run often, but source code is run never.

New comment by e____g in "How plants communicate with each other when in danger"

e____g — Sun, 22 Oct 2023 07:22:45 +0000

I think vegans already grok this. My understanding is that the vegan diet is not the manifestation of a love for animals but rather the embodiment of a hatred of vegetables.

New comment by e____g in "Advanced Linux Programming (2001)"

e____g — Sun, 09 Apr 2023 06:59:46 +0000

(2001)

New comment by e____g in "Tell HN: Prompt leaking is the most scifi thing ever"

e____g — Thu, 09 Feb 2023 06:56:45 +0000

I imagine it's because we use the tools we know. There are likely more effective approaches that would look like gibberish, but we don't have the insight to use those. All we have is the English hammer, so we approach every problem as if it were an English nail.

New comment by e____g in "Tangled issues with permanent HTTP redirects"

e____g — Fri, 23 Sep 2022 06:10:01 +0000

The problem is that perfectly distinguishing permanent and temporary redirects requires infallible knowledge of the future, which is not possible.

New comment by e____g in "Why does gRPC insist on trailers?"

e____g — Mon, 08 Aug 2022 04:26:59 +0000

This is very much not it. The Stubby team decided early on to use trailers and was combative and obstinate when the Chrome and GFE (reverse proxy) teams tried to explain why doing so would be a bad idea. The use of trailers in gRPC originates in the hubris of one team, not a conspiracy by Google.

New comment by e____g in "The smallest 256x256 single-color PNG file, and where you've seen it (2015)"

e____g — Fri, 22 Apr 2022 03:03:17 +0000

brotli helps:

  $ echo '' | brotli -9 - | wc -c
  93

New comment by e____g in "Google has a typo on its bad request page"

e____g — Wed, 09 Jun 2021 20:07:08 +0000

That's the joke.