<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: thallukrish</title><link>https://news.ycombinator.com/user?id=thallukrish</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 15 Apr 2026 19:34:28 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=thallukrish" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by thallukrish in "Opus 4.5 is not the normal AI agent experience that I have had thus far"]]></title><description><![CDATA[
<p>When complexity increases, you end up handholding them in pieces.</p>
]]></description><pubDate>Wed, 07 Jan 2026 04:38:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=46522620</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=46522620</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46522620</guid></item><item><title><![CDATA[New comment by thallukrish in "SymbolicAI: A neuro-symbolic perspective on LLMs"]]></title><description><![CDATA[
<p>Yes. That seems to be the case.
While it may not be saving any time compared to generating general python code vs. specific symbolic code, the real value could be that it has an engine to enforce the contract on LLM responses with the library or even do the calls to the LLM as a common piece of code making it less error prone and bringing consistency in the interactions with the LLM.</p>
]]></description><pubDate>Sat, 28 Jun 2025 03:34:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=44402144</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=44402144</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44402144</guid></item><item><title><![CDATA[New comment by thallukrish in "SymbolicAI: A neuro-symbolic perspective on LLMs"]]></title><description><![CDATA[
<p>Since code is generated by LLM these days, how does specific syntactic constructs like a Symbol which essentially carries the context and can be manipulated with python operators help when compared to a normal python code generated by LLM with all the checks and balances instructed by a human?
For example, I can write in this syntax to convert all fruits to vegetables or I can simply prompt an LLM to construct a program that takes a list of fruits and calls a LLM in the background to return the vegetables equivalent. 
I am trying to understand the difference.</p>
]]></description><pubDate>Sat, 28 Jun 2025 03:08:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=44402063</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=44402063</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44402063</guid></item><item><title><![CDATA[New comment by thallukrish in "Johnny.Decimal – A system to organise your life"]]></title><description><![CDATA[
<p>The problem with organizing is not the lack of tools or techniques.
It is simply not possible to devise a system which works automatically with little effort.
Everything requires varying levels of discipline which is hard to keep up with time and a different situation.</p>
]]></description><pubDate>Sat, 22 Feb 2025 03:53:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=43135937</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=43135937</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43135937</guid></item><item><title><![CDATA[Programming with Punch Cards [pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="https://web.archive.org/web/20090325223903/https://www.columbia.edu/acis/history/fisk.pdf">https://web.archive.org/web/20090325223903/https://www.columbia.edu/acis/history/fisk.pdf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41151057">https://news.ycombinator.com/item?id=41151057</a></p>
<p>Points: 22</p>
<p># Comments: 5</p>
]]></description><pubDate>Sun, 04 Aug 2024 03:52:17 +0000</pubDate><link>https://web.archive.org/web/20090325223903/https://www.columbia.edu/acis/history/fisk.pdf</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=41151057</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41151057</guid></item><item><title><![CDATA[New comment by thallukrish in "Recursive Recipes"]]></title><description><![CDATA[
<p>this is like minecraft.</p>
]]></description><pubDate>Sun, 15 Oct 2023 09:00:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=37888158</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=37888158</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37888158</guid></item><item><title><![CDATA[New comment by thallukrish in "How to find time to learn after work (2017)"]]></title><description><![CDATA[
<p>Don't find time for something.
Find something that takes your time.</p>
]]></description><pubDate>Tue, 29 Aug 2023 02:56:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=37303024</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=37303024</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37303024</guid></item><item><title><![CDATA[Ask HN: Is AI a glorified memory machine?]]></title><description><![CDATA[
<p>If every problem is bounded by a bunch of data points on a multi-dimensional plane, and some sort of clustering is done on them that reflects the problem domain, then isn't running through the samples during training equivalent to memorizing them and associating them and allowing for a small margin of error making it look like the model is able to generalize.
In short, doesn't that just boil down to how good we made our samples and setting the whole process in a way to memorize those samples ?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=37245339">https://news.ycombinator.com/item?id=37245339</a></p>
<p>Points: 5</p>
<p># Comments: 5</p>
]]></description><pubDate>Thu, 24 Aug 2023 05:25:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=37245339</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=37245339</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37245339</guid></item><item><title><![CDATA[New comment by thallukrish in "OpenAI ChatGPT: Optimizing language models for dialogue"]]></title><description><![CDATA[
<p>Will it give the same answer for a question or change the answers every time you ask it ? Just curious.</p>
]]></description><pubDate>Thu, 01 Dec 2022 10:29:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=33814519</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=33814519</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33814519</guid></item><item><title><![CDATA[New comment by thallukrish in "The Problem with Intelligence"]]></title><description><![CDATA[
<p>Humans seem to do a million different things. And all of them were kids growing into adults and do by learning to do things.
Isn't that good enough if a machine did just that - ready to learn if taught, to be classified as being generally intelligent ?</p>
]]></description><pubDate>Thu, 15 Sep 2022 14:25:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=32852550</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=32852550</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32852550</guid></item><item><title><![CDATA[New comment by thallukrish in "More content by people, for people in Search"]]></title><description><![CDATA[
<p>What if unique content is not the one I want?</p>
]]></description><pubDate>Fri, 19 Aug 2022 10:05:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=32519218</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=32519218</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32519218</guid></item><item><title><![CDATA[New comment by thallukrish in "The Creator's Dilemma"]]></title><description><![CDATA[
<p>I've been a dev building things and I can resonate with what you say very much. 
A builder is like someone who has a hammer in his hand with everything around looking like a nail.
Esp. if you are a builder who is constantly excited with your own ideas, it's hard to ask who would want that ?</p>
]]></description><pubDate>Tue, 19 Jul 2022 06:23:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=32148171</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=32148171</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32148171</guid></item><item><title><![CDATA[The Creator's Dilemma]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.ryanckulp.com/creators-dilemma/">https://www.ryanckulp.com/creators-dilemma/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=32147894">https://news.ycombinator.com/item?id=32147894</a></p>
<p>Points: 2</p>
<p># Comments: 4</p>
]]></description><pubDate>Tue, 19 Jul 2022 05:34:44 +0000</pubDate><link>https://www.ryanckulp.com/creators-dilemma/</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=32147894</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32147894</guid></item><item><title><![CDATA[New comment by thallukrish in "Why Google is so unbearable, and how to fix it"]]></title><description><![CDATA[
<p>There is no perfect answer for a query.
There can only be contextually meaningful answers. 
They can be from highly relevant to far off.
It is very hard to prove a search engine as bad in general.
It may not work for you. But it may still work for a lot more.
Google has indexed the entire Web. This is as large a span as one can take.</p>
]]></description><pubDate>Wed, 18 May 2022 13:25:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=31422469</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=31422469</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=31422469</guid></item><item><title><![CDATA[New comment by thallukrish in "Sounding the alarm: How noise hurts the heart (2021)"]]></title><description><![CDATA[
<p>Wrote this during the lockdown.<p><a href="https://thallukrish.medium.com/noise-and-well-being-a9f0b30d55a6" rel="nofollow">https://thallukrish.medium.com/noise-and-well-being-a9f0b30d...</a></p>
]]></description><pubDate>Mon, 11 Apr 2022 07:05:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=30985578</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30985578</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30985578</guid></item><item><title><![CDATA[New comment by thallukrish in "Back to India"]]></title><description><![CDATA[
<p>Actually the place does not matter if you have dreams bigger than the place. Pursue them wherever it makes sense. If your dream is to build a startup go build it. If it should be done in India or Timbuktoo, go do it there. 
Just because you stay in the US or Europe, doesn't mean you can have better dreams. You may be among those who are able to dream better. It may give you better clues as to how to dream compared to India. 
But hey, in a flat world, you can dream sitting anywhere and go for it wherever you are. It may be a bit harder to do things in India. But without a doubt, the number of problems you can solve in India is far greater than developed countries. In that sense, if you are done with all the Education and stuff and you are reasonably good on finances, India is a lot cheaper to sit and dream and make things happen.</p>
]]></description><pubDate>Sat, 09 Apr 2022 08:39:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=30966260</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30966260</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30966260</guid></item><item><title><![CDATA[New comment by thallukrish in "Ask HN: What makes people add links to HN?"]]></title><description><![CDATA[
<p>Unless you are outright promoting commercial stuff, I feel for writers who are relatively unknown and would like to get feedback on what they write, HN is a good place to post links.<p>This is not different from posting interesting links you find. It is not self-promotion as you are not selling anything here. Instead you are trying to see if the content resonates with others and kickstarts a discussion.<p>In fact, I see it as no different from the comments we are writing here.</p>
]]></description><pubDate>Mon, 28 Mar 2022 03:14:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=30826740</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30826740</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30826740</guid></item><item><title><![CDATA[Ask HN: What makes people add links to HN?]]></title><description><![CDATA[
<p>I wonder what motivates people to add links to HN ? I have added many of my blogs in the hope that people will read / discuss about it.
But for those who add links to HN is it the discussion from the community the only thing?
And most times the comments are very interesting to read, but beyond that does it really translate into commerce and connections for people ?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=30792481">https://news.ycombinator.com/item?id=30792481</a></p>
<p>Points: 4</p>
<p># Comments: 4</p>
]]></description><pubDate>Thu, 24 Mar 2022 16:55:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=30792481</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30792481</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30792481</guid></item><item><title><![CDATA[New comment by thallukrish in "Happiness and the Art of Being (2012)"]]></title><description><![CDATA[
<p>The more you think about enlightenment, the more you are away from it.</p>
]]></description><pubDate>Thu, 24 Mar 2022 16:48:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=30792393</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30792393</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30792393</guid></item><item><title><![CDATA[New comment by thallukrish in "Ask HN: How do you deal with getting old and feeling lost?"]]></title><description><![CDATA[
<p>oh you are spot on with your feelings. And you can do nothing about it. You will figure out however something that will work for you and move on with life. I could've told this and that. But I just want to be honest.</p>
]]></description><pubDate>Sun, 06 Feb 2022 15:26:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=30233314</link><dc:creator>thallukrish</dc:creator><comments>https://news.ycombinator.com/item?id=30233314</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30233314</guid></item></channel></rss>