<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Archives on rkar.org</title><link>https://rkar.org/archive/</link><description>Recent content in Archives on rkar.org</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 24 Feb 2026 22:04:41 +1300</lastBuildDate><atom:link href="https://rkar.org/archive/index.xml" rel="self" type="application/rss+xml"/><item><title>Solving Bongard Problems using VLMs</title><link>https://rkar.org/archive/03_bongard_vlm/</link><pubDate>Thu, 28 Aug 2025 00:00:00 +0000</pubDate><guid>https://rkar.org/archive/03_bongard_vlm/</guid><description>&lt;p>
In 2018, this &lt;a href="https://k10v.github.io/2018/02/25/Solving-Bongard-problems-with-deep-learning/">post&lt;/a> made an interesting attempt at solving Bongard
problems using deep learning. That work may have laid the foundation
for further attempts at creating various Bongard-like datasets such as
Bongard-LOGO&lt;sup class="footnote-reference">&lt;a id="footnote-reference-1" href="#footnote-1">1&lt;/a>&lt;/sup>, Bongard-HOI&lt;sup class="footnote-reference">&lt;a id="footnote-reference-2" href="#footnote-2">2&lt;/a>&lt;/sup>, and Bongard-OpenWorld&lt;sup class="footnote-reference">&lt;a id="footnote-reference-3" href="#footnote-3">3&lt;/a>&lt;/sup>.
This post is an attempt to replicate the same methodology with
state-of-the-art vision-language models (VLMs).&lt;/p>
&lt;div id="outline-container-a-quick-intro" class="outline-2">
&lt;h2 id="a-quick-intro">
A Quick Intro
&lt;/h2>
&lt;div id="outline-text-a-quick-intro" class="outline-text-2">
&lt;p>
Bongard Problems are puzzles formulated by Russian scientist and
intelligence theorist Mikhail Moiseevich Bongard in the 1960s in his
book &lt;strong>The Problem of Recognition&lt;/strong> (&lt;strong>Problema Uznavaniya&lt;/strong>). A typical
Bongard problem consists of two sets of six images. All images on one
side illustrate a shared concept that is absent from the other side.&lt;/p></description></item><item><title>Agentic Programming is No Fun</title><link>https://rkar.org/archive/02_agentic_programming/</link><pubDate>Wed, 25 Jun 2025 00:00:00 +0000</pubDate><guid>https://rkar.org/archive/02_agentic_programming/</guid><description>&lt;p>
This post is based on my personal experience after dabbling with
AI-based agentic programming for a few days. Not that anyone actively
reads my blog, but I want to document how I am feeling at this point
in time, during what feels like the early rise of AI automation.&lt;/p>
&lt;div id="outline-container-how-i-use-ai-today" class="outline-2">
&lt;h2 id="how-i-use-ai-today">
How I Use AI Today
&lt;/h2>
&lt;div id="outline-text-how-i-use-ai-today" class="outline-text-2">
&lt;p>
I have been consistently using AI chatbots over the past couple of
years for programming-related tasks. I barely Google error messages
anymore; I just paste them into ChatGPT or Claude and move on. I am on
the free tiers now, but I did subscribe for a few months after
realizing Claude was better at generating code.&lt;/p></description></item><item><title>Elegance is in the Eye of the Beholder</title><link>https://rkar.org/archive/01_elegance_beholder/</link><pubDate>Sun, 08 Dec 2024 00:00:00 +0000</pubDate><guid>https://rkar.org/archive/01_elegance_beholder/</guid><description>&lt;div id="outline-container-introduction" class="outline-2">
&lt;h2 id="introduction">
Introduction
&lt;/h2>
&lt;div id="outline-text-introduction" class="outline-text-2">
&lt;p>
&lt;a href="https:go.dev">Go&lt;/a> recently added support for a syntax that a fellow gopher had
requested 12 years ago on the &lt;a href="https://groups.google.com/g/golang-nuts/c/7J8FY07dkW0/m/iwSs6_Q3AAAJ">forum&lt;/a>. The OP proposed a range syntax
for Go that was &amp;#34;simpler&amp;#34; than the traditional C-like iteration.&lt;/p>
&lt;p>
The discussion that followed highlighted an interesting divide - while
a few found the proposed syntax cleaner, others argued that the
traditional C-style loop was more explicit and natural, especially for
developers with C background. This debate about what makes loop syntax
&amp;#34;elegant&amp;#34; has historical roots.&lt;/p></description></item></channel></rss>