<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Posts on Kin Ian Lo</title>
    <link>https://kinianlo.github.io/posts/</link>
    <description>Recent content in Posts on Kin Ian Lo</description>
    <image>
      <title>Kin Ian Lo</title>
      <url>https://kinianlo.github.io/images/papermod-cover.png</url>
      <link>https://kinianlo.github.io/images/papermod-cover.png</link>
    </image>
    <generator>Hugo -- 0.127.0</generator>
    <language>en</language>
    <lastBuildDate>Mon, 17 Jun 2024 01:06:04 +0000</lastBuildDate>
    <atom:link href="https://kinianlo.github.io/posts/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Another derivation for &#34;Obtaining logprobs from an LLM API&#34;</title>
      <link>https://kinianlo.github.io/posts/llm-api-probs/</link>
      <pubDate>Mon, 17 Jun 2024 01:06:04 +0000</pubDate>
      <guid>https://kinianlo.github.io/posts/llm-api-probs/</guid>
      <description>OpenAI has modified their API to return the log probabilities before any logit bias is applied. Hence the methods described in this article are no longer applicable.
The aim of this article is to provide an alternative derivation of the results in Mattew Finlayson&amp;rsquo;s article Obtaining logprobs from an LLM API.
Most LLM APIs return the logprobs of only the top-$ k $ predictions. The value of $ k $ is often small, in the order of 10.</description>
    </item>
    <item>
      <title>Notes on Statistics</title>
      <link>https://kinianlo.github.io/posts/2023-02-12-stats/</link>
      <pubDate>Sun, 12 Feb 2023 01:06:04 +0000</pubDate>
      <guid>https://kinianlo.github.io/posts/2023-02-12-stats/</guid>
      <description>some notes on hypothesis testing and bootstrapping</description>
    </item>
    <item>
      <title>Writing LaTex maths in markdown</title>
      <link>https://kinianlo.github.io/posts/2023-02-09-maths-in-markdown/</link>
      <pubDate>Thu, 09 Feb 2023 23:10:42 +0000</pubDate>
      <guid>https://kinianlo.github.io/posts/2023-02-09-maths-in-markdown/</guid>
      <description>This article records the pain I went through to write maths in markdown</description>
    </item>
    <item>
      <title>Notes on binary search</title>
      <link>https://kinianlo.github.io/posts/2022-10-17-bisect/</link>
      <pubDate>Mon, 17 Oct 2022 12:27:46 +0000</pubDate>
      <guid>https://kinianlo.github.io/posts/2022-10-17-bisect/</guid>
      <description>On the implementation of binary search</description>
    </item>
  </channel>
</rss>
