Hacker News: 4by4by4

New comment by 4by4by4 in "DeepInfer: High-performance inference framework for DeepSeek models"

4by4by4 — Tue, 20 Oct 2026 13:23:47 +0000

Does anyone have rough numbers on how this compares to vLLM in terms of price performance? Maybe with something like Dynamo for disaggregated serving and KV-aware routing.

I'm curious if it's a modest increase in performance or a significant one.

New comment by 4by4by4 in "Benchmarking Opus 5 on SlopCodeBench"

4by4by4 — Tue, 28 Jul 2026 04:09:31 +0000

I'd be curious to see the raw test results.

I have a suspicion that most models will miss the `database_migration` Checkpoint 2 test that includes a `default_value` because it could be interpreted as either a JSON-literal or a SQL-expression.

There might be other tests as well that are prone to failure for reasons other than the reasons cited in the paper.

I think a cool experiment would be to adjust the order of the features implemented (e.g. checkpoint 3 then 2 then 5 then 4) where dependencies allow it. Then one could account for some checkpoints being more difficult than others.

New comment by 4by4by4 in "A full body MRI earns you a year of smoking"

4by4by4 — Mon, 13 Jul 2026 19:17:45 +0000

> So the same effort you would expend to get out of those activities [such as one year of smoking] on account of their risk, the same effort you should be willing to expend to get a full-body mri

That's the conclusion of the article, which I didn't immediately understand from the title. I read "earns" as a negative reward, not a positive one.

Deepgram raises $130M at $1.3B valuation and buys a YC AI startup

4by4by4 — Tue, 13 Jan 2026 21:08:21 +0000

Article URL: https://techcrunch.com/2026/01/13/deepgram-raises-130m-at-1-3b-valuation-and-buys-a-yc-ai-startup/

Comments URL: https://news.ycombinator.com/item?id=46608043

Points: 1

# Comments: 0

New comment by 4by4by4 in "Television: Fast general purpose fuzzy finder TUI"

4by4by4 — Fri, 10 Jan 2025 03:44:20 +0000

This seems similar to fzf with a nice default experience (quick access to fuzzy search files, shell history, git log) and a subset of features.

I use fzf to hack together custom TUIs (a calculator, clipboard search, quick LLM chat). The killer feature for me is `--bind` to bind keys and events to custom actions.

New comment by 4by4by4 in "SeaweedFS fast distributed storage system for blobs, objects, files and datalake"

4by4by4 — Fri, 02 Feb 2024 23:48:25 +0000

That would be nice and that’s why we first tried MinIO.

But with MinIO and erasure coding a single PUT results in more IOPS and we saw lower performance.

Also, expanding MinIO must be done in increments of your original buildout which is annoying. So if you start with 4 servers and 500TB, they recommend you expand by adding another 4 servers with 500TB at least.

New comment by 4by4by4 in "SeaweedFS fast distributed storage system for blobs, objects, files and datalake"

4by4by4 — Fri, 02 Feb 2024 23:45:18 +0000

Not the only reason, but we have a distributed workload so HTTP is a better protocol than NFS for our use case.

New comment by 4by4by4 in "SeaweedFS fast distributed storage system for blobs, objects, files and datalake"

4by4by4 — Fri, 02 Feb 2024 23:20:15 +0000

Setup is a little obscure, but the developer is responsive on Slack and GH.

We are only a couple months in and haven’t had to add to our cluster yet, storing about 250TB, so it’s still early for us. Promising so far and hardware has already paid for itself.

New comment by 4by4by4 in "SeaweedFS fast distributed storage system for blobs, objects, files and datalake"

4by4by4 — Fri, 02 Feb 2024 23:13:32 +0000

We tested both SeaweedFS and Min.io for cheaply (HDD) storing > 100TB of audio data.

Seaweed had much better performance for our use case.

New comment by 4by4by4 in "LazyVim"

4by4by4 — Mon, 17 Jul 2023 02:40:38 +0000

Using LazyVim got me over the hump to switch to neovim from vscode. My previous attempts failed when it took too long to get an IDE-compatible setup. I suppose I am the type of person that wants and IDE/editor that lives in the terminal!

New comment by 4by4by4 in "Ain't it funny how the knight moves?"

4by4by4 — Fri, 20 Jan 2023 23:38:20 +0000

As a teenager I had a chess lesson with Ben Finegold and I practiced this puzzle for weeks on a physical board.

He also mentioned this riddle off hand which I had a ton of fun solving. https://fivethirtyeight.com/features/how-about-a-nice-game-o...

New comment by 4by4by4 in "Show HN: Speech Racer – A speaking test for speed and accuracy"

4by4by4 — Fri, 18 Nov 2022 13:49:19 +0000

Hi HN! This game is similar to typing tests (e.g. typings.gg) but for speech. Hope you enjoy!

Show HN: Speech Racer – A speaking test for speed and accuracy

4by4by4 — Fri, 18 Nov 2022 11:48:25 +0000

Article URL: https://speechracer.com/

Comments URL: https://news.ycombinator.com/item?id=33653332

Points: 2

# Comments: 1

New comment by 4by4by4 in "What SRE Could Be"

4by4by4 — Mon, 06 Jun 2022 23:50:51 +0000

I’m curious what services you interact with that have five nines availability. Most services that I interact with, AWS APIs as an example, top out at an SLA of four nines for availability.

New comment by 4by4by4 in "Why enterprise software is bloated"

4by4by4 — Thu, 03 Mar 2022 13:59:09 +0000

I have a four month old and was inspired to buy one outfit with magnets because of this tweet. It works fairly well, but is no better than a single zipper outfit and is much more expensive.

New comment by 4by4by4 in "Who is the most accurate world chess champion?"

4by4by4 — Sat, 04 Dec 2021 20:32:54 +0000

I’ve thought about this, too. Sadly, times only started being recorded in the last 20 years and last time I tried I couldn’t find a large dataset with the times included.

Chess.com did do one study and found a large percentage of mistakes occurs in moves 36-40 because in some time controls additional time is added at move 40.

New comment by 4by4by4 in "Who is the most accurate world chess champion?"

4by4by4 — Sat, 04 Dec 2021 17:22:33 +0000

True, it’s works differently though. And Stockfish does not compute win/draw/loss probabilities as part of its eval. It converts cp to wdl using an exponential fit based stockfish vs stockfish games. So draw percentage in Leela is a lot more interesting and useful.

New comment by 4by4by4 in "Who is the most accurate world chess champion?"

4by4by4 — Sat, 04 Dec 2021 15:48:34 +0000

In my opinion, neural network engines like Alpha Zero or Leela Zero do a much better job of assessing how difficult a position is to hold. They also report the evaluation in a completely different manner, win/draw/loss probability as opposed to centipawn loss.

For example, in yesterday’s game Stockfish was often giving a drawn evaluation (0.00) where Leela Chess gave a win probability of 30%+. I was posting about this during the game.

https://twitter.com/nik_king_/status/1466794534214504454?s=2...

New comment by 4by4by4 in "My salary as a full-stack developer"

4by4by4 — Wed, 12 May 2021 19:09:49 +0000

I agree with others that your salary is low. Another important question is: how much would you like to make?