Hacker News: sgk284

Three Years of Predicting Football with LLMs

sgk284 — Fri, 06 Feb 2026 19:29:34 +0000

Article URL: https://bits.logic.inc/p/three-years-of-predicting-football

Comments URL: https://news.ycombinator.com/item?id=46917060

Points: 2

# Comments: 0

On The Obsolescence of Interns in the Age of AI

sgk284 — Wed, 31 Dec 2025 20:03:13 +0000

Article URL: https://bits.logic.inc/p/interning-in-2026

Comments URL: https://news.ycombinator.com/item?id=46447732

Points: 3

# Comments: 0

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Tue, 30 Dec 2025 06:57:17 +0000

Yep, 100% correct. We're still reviewing and advising on test cases. We also write a PRD beforehand (with the LLM interviewing us!) so the scope and expectations tend to be fairly well-defined.

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Tue, 30 Dec 2025 01:20:55 +0000

It doesn't require removing them if you think you'll need them. It just requires writing tests for those edge cases so you have confidence that the code will work correctly if/when those branches do eventually run.

I don't think anyone wants production code paths that have never been tried, right?

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Tue, 30 Dec 2025 00:00:28 +0000

FWIW all of the content on our eng blog is good ol' cage-free grass-fed human-written content.

(If the analogy, in the first paragraph, of a Roomba dragging poop around the house didn't convince you)

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Mon, 29 Dec 2025 22:20:17 +0000

I suspect it will still fall on humans (with machine assistance?) to move the field forward and innovate, but in terms of training an LLM on genuinely new concepts, they tend to be pretty nimble on that front (in my experience).

Especially with the massive context windows modern LLMs have. The core idea that the GPT-3 paper introduced was (summarizing):

  A sufficiently large language model can perform new tasks it has never seen using only a few examples provided at inference time, without any gradient updates or fine-tuning.

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Mon, 29 Dec 2025 22:14:13 +0000

I never claim that 100% coverage has anything to do with code breaking. The only claim made is that anything less than 100% does guarantee that some piece of code is not automatically exercised, which we don't allow.

It's a footnote on the post, but I expand on this with:

  100% coverage is actually the minimum bar we set. We encourage writing tests for as many scenarios as is possible, even if it means the same lines getting exercised multiple times. It gets us closer to 100% path coverage as well, though we don’t enforce (or measure) that

New comment by sgk284 in "AI is forcing us to write good code"

sgk284 — Mon, 29 Dec 2025 22:06:24 +0000

Can you say more? I see a lot of teams struggling with getting AI to work for them. A lot of folks expect it to be a little more magical and "free" than it actually is. So this post is just me sharing what works well for us on a very seasoned eng team.

AI is forcing us to write good code

sgk284 — Mon, 29 Dec 2025 19:11:26 +0000

Article URL: https://bits.logic.inc/p/ai-is-forcing-us-to-write-good-code

Comments URL: https://news.ycombinator.com/item?id=46424200

Points: 302

# Comments: 216

Engineering Is Becoming Beekeeping

sgk284 — Sun, 28 Dec 2025 19:00:31 +0000

Article URL: https://bits.logic.inc/p/engineering-is-becoming-beekeeping

Comments URL: https://news.ycombinator.com/item?id=46413486

Points: 2

# Comments: 0

Your Team Uses AI. Why Aren't You 10x Faster?

sgk284 — Sat, 27 Dec 2025 19:18:33 +0000

Article URL: https://bits.logic.inc/p/my-team-is-using-ai-why-arent-they

Comments URL: https://news.ycombinator.com/item?id=46404332

Points: 5

# Comments: 1

Machine-Driven Code Review

sgk284 — Fri, 26 Dec 2025 22:35:54 +0000

Article URL: https://bits.logic.inc/p/code-review-without-bottlenecks

Comments URL: https://news.ycombinator.com/item?id=46397102

Points: 1

# Comments: 0

New comment by sgk284 in "Using Vectorize to build an unreasonably good search engine in 160 lines of code"

sgk284 — Thu, 25 Dec 2025 11:23:28 +0000

Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking.

We open-sourced our impl just this week: https://github.com/with-logic/intent

We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.

If you use mini / flash models from OpenAI / Gemini, expect it to be 2.5s-3s of overhead.