Top all-time · #19749
Jacob Brazeal
Personal blog · jacobbrazeal.wordpress.comcareerprogramming
Jacob Brazeal's personal blog at jacobbrazeal.wordpress.com covers career and programming. Since 2020, 3 different Hacker News readers have linked it 30 times, most often “Using GPT-3 to pathfind in random graphs”. It is still writing: the last post was on 2026-05-03, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN commenters cite this blog's GPT-3 post as the article that shaped one commenter's view of AI capabilities, and link it again in a discussion of emergent abilities in large language models.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Using GPT-3 to pathfind in random graphs3 people · 4 mentions · first linked 2022-09-23
What Hacker News says?
Hey, OP here - thanks for this wonderful comment. I'd like to hijack this thread to say that I respond to this comment and several other questions here - https://jacobbrazeal.wordpress.com/2020/11/17/the-touching-r... . Thank you all for such a warm reception.
Comment linking /2020/11/17/the-touching-responses-to-on-learning-chess/
on “On Learning Chess as an Adult – From 650 to 1750 in Two Years”Submitted On Learning Chess as an Adult – From 650 to 1750 in Two Years as a story · 556 points
HN discussionI made a solver for this and did some comparison with Wordle: https://jacobbrazeal.wordpress.com/2022/02/07/solving-nerdle... . TL;DR even though there's an order of magnitude more possible words, you can solve it in fewer average guesses than Wordle pretty consistently.
Comment linking /2022/02/07/solving-nerdle/
on “Nerdle = Like Wordle but with Equations”Submitted Using GPT-3 to pathfind in random graphs as a story · 165 points
HN discussionFor me it was this article: https://jacobbrazeal.wordpress.com/2022/09/23/gpt-3-can-find... And then following comment chain with another example: https://news.ycombinator.com/item?id=32960083
Comment linking /2022/09/23/gpt-3-can-find-paths-up-to-7-nodes-long-in-random-graphs/
on “Planning for AGI and Beyond”Submitted 6 months of working at a hypergrowth startup as a story · 105 points
HN discussionWhat about this "emergent" intelligence when size of the model is large enough? There are blogs about it being able to model problems internally or forming a mini NN of its own. As I've understood, even the researchers in the field have no idea why this happens. It's completely empirical and a "discovered phenomenon" at this point. [1]: https://www.jasonwei.net/blog/emergence [2]: https://jacobbrazeal.wordpress.com/…
Comment linking /2022/09/23/gpt-3-can-find-paths-up-to-7-nodes-long-in-random-graphs/
on “Ask HN: Have you lost enthusiasm for programming and learning after ChatGPT?”Submitted Those computers in your head as a story · 66 points
HN discussionSubmitted Fixing the mechanics of my bullet chess as a story · 40 points
HN discussionSubmitted A puzzle of two unreliable sensors as a story · 18 points
HN discussionSubmitted Where the Cameos Are as a story · 5 points
HN discussionSubmitted Using GPT-3 to pathfind in random graphs as a story · 4 points
HN discussionSubmitted Looking back on Stripe's payment API migration as a story · 3 points
HN discussionSubmitted Find what you're missing at zombo.com as a story · 3 points
HN discussionSubmitted Baseball, Pitcher Wins, and Life as a story · 3 points
HN discussionSubmitted It would take just one glorious Haskell PR as a story · 3 points
HN discussionSubmitted Cancer as a story · 2 points
HN discussionSubmitted Advice for System Design Interviews as a story · 2 points
HN discussionSubmitted Nine Aaron Judges as a story · 2 points
HN discussionSubmitted Why are you telling me this? as a story · 2 points
HN discussionSubmitted Why are you telling me this? as a story · 2 points
HN discussionSubmitted How to build internal tools as a story · 2 points
HN discussionSubmitted Is Nerdle Harder Than Wordle? as a story · 2 points
HN discussionSubmitted The touching responses to “On learning chess” as a story · 2 points
HN discussionSubmitted Review: Machines of Loving Grace as a story · 1 points
HN discussionSubmitted The Perfect Advertisement as a story · 1 points
HN discussionSubmitted On not noticing rather too many things as a story · 1 points
HN discussionSubmitted Computationally optimal arrangements of barbell plates as a story · 1 points
HN discussionSubmitted Computationally optimal sequences of barbell plates as a story · 1 points
HN discussionSubmitted Speculative Autobiographies as a story · 1 points
HN discussion