<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: abhishekbasu</title><link>https://news.ycombinator.com/user?id=abhishekbasu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 05:13:59 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=abhishekbasu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>love the website, but quality control is important when working with these agents.<p>ex. i tried cool walk (<a href="https://wooten-labs.com/coolwalk" rel="nofollow">https://wooten-labs.com/coolwalk</a>) and the 'Download on the App Store' does nothing at all.</p>
]]></description><pubDate>Thu, 05 Nov 2026 08:19:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=50376565</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=50376565</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50376565</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Skill to Create Product Videos"]]></title><description><![CDATA[
<p>I highly doubt this skill adds much. Even prior to Opus 5.5 these models were good enough to generate videos, look at the demos on <a href="https://fretta.ai" rel="nofollow">https://fretta.ai</a> for example.<p>Adding audio and sfx is easy too if you add ElevenLabs to the mix.</p>
]]></description><pubDate>Tue, 03 Nov 2026 08:58:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=50349659</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=50349659</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50349659</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Herdr has released native app"]]></title><description><![CDATA[
<p>agreed, this is a huge pet peeve of mine. every app that has a frontend should have screenshots on their github</p>
]]></description><pubDate>Sat, 31 Oct 2026 04:08:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=50313122</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=50313122</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50313122</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: Thoughts on hiring junior engineers in 2026?"]]></title><description><![CDATA[
<p>Thanks for sharing. Do you have a few examples of these human bottlenecks where a junior engineer is apt?</p>
]]></description><pubDate>Fri, 16 Oct 2026 14:30:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=50118815</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=50118815</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50118815</guid></item><item><title><![CDATA[Ask HN: Thoughts on hiring junior engineers in 2026?]]></title><description><![CDATA[
<p>Just started hiring for my AI x Freight startup. To vet junior hires I'm offering them paid internships (above median market pay) before making a FT hire decision.<p>So far, I'm really struggling to see the value add of a junior engineer given how good the models have become. A senior with Max plan beats three junior hires (very rough estimate).<p>Having spoken with a few peers (founders), they have expressed similar feelings. I want to hire juniors and see them grow, but I feel my bar of expectations is at an all time high, and perhaps unrealistic.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50118474">https://news.ycombinator.com/item?id=50118474</a></p>
<p>Points: 13</p>
<p># Comments: 27</p>
]]></description><pubDate>Fri, 16 Oct 2026 13:59:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=50118474</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=50118474</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50118474</guid></item><item><title><![CDATA[New comment by abhishekbasu in "[dead]"]]></title><description><![CDATA[
<p>Interesting read, as someone who chose not to pursue an MBA after my technical masters in '18 I wonder if there is any value aside from time to explore when pursuing an MBA in '26</p>
]]></description><pubDate>Thu, 24 Sep 2026 03:38:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=49825950</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=49825950</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49825950</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Thank you for your kind words! Your marketplace idea definitely sounds interesting to me, if not for payments, it would definitely provide a way to improve visibility through easier data exchange due to a common platform.</p>
]]></description><pubDate>Thu, 12 Feb 2026 13:21:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=46988524</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46988524</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46988524</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Hosted on premise for enterprise, VPC for mid market customers. For enterprise customers, FDE model makes most sense for a product like this and they would assist with implementation and training. For mid market customers, I'm still exploring options to make it cost effective.<p>For domain-specific optimization, the value is in the solver integrations, specific constraints that form the seed, and the modular simulation that powers the visuals. The software is monetized, not the services around it.<p>> How will you stop LLMs from recreating it?
Having worked this space for a while now I think there are two ways to ensure reliability (the real moat here), first is going deep into five-six problems that are complex enough that out of box solutions/simple prompting don't work well. Second, tightly coupling a simulator to provide rapid feedback that actually helps change manage and solve the "people" problem when optimizing operations.</p>
]]></description><pubDate>Wed, 11 Feb 2026 07:47:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=46972081</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46972081</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46972081</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Also, this was a quick fun project for a multi-agent flow <a href="https://flickfeast.party/" rel="nofollow">https://flickfeast.party/</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 16:11:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=46946818</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46946818</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46946818</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Developing LogiModel AI (<a href="https://www.logimodel.com/" rel="nofollow">https://www.logimodel.com/</a>) which is an agentic supply chain optimization engine that forecasts demand, optimizes operations, and simulates scenarios to reduce costs while keeping your network reliable and customers satisfied. It integrates seamlessly with your ERP and document repositories to learn your business context, then acts as an intelligent decision engine, freeing you to focus on strategy while it handles execution.<p>Always interested in possibilities of LLMs interfacing with MIP solvers.</p>
]]></description><pubDate>Mon, 09 Feb 2026 14:50:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=46945821</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46945821</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46945821</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Pokémon Team Optimization"]]></title><description><![CDATA[
<p>you're right, it should be (3,0) with optimal obj value of 6.</p>
]]></description><pubDate>Thu, 01 Jan 2026 09:04:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=46452491</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46452491</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46452491</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Pokémon Team Optimization"]]></title><description><![CDATA[
<p>this was a great read to start the new year! having worked extensively with mixed integer programs, it is always a bit disheartening to see them not used enough for everyday decision-making. one of my goals this year is to create a layer to make it easier to formulate mips and test them, via plain text input. this would hopefully increase adoption through a lower barrier to entry.</p>
]]></description><pubDate>Thu, 01 Jan 2026 08:47:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=46452411</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=46452411</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46452411</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Launch HN: Plexe (YC X25) – Build production-grade ML models from prompts"]]></title><description><![CDATA[
<p>Great product and congratulations on the launch. Who is the target user vs  customer? On the surface, and I may be wrong here, this feels like a LLM layered on top of a typical AutoML structure eg: TPOT, Caret. Is that the correct mental model for a tool like this? And if so, do you see a similar problem that these tools faced in broader adoption at companies?</p>
]]></description><pubDate>Thu, 06 Nov 2025 05:53:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=45831927</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=45831927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45831927</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Grokipedia by xAI"]]></title><description><![CDATA[
<p>Grokipedia at home: <a href="https://github.com/abhishekbasu/localwiki" rel="nofollow">https://github.com/abhishekbasu/localwiki</a></p>
]]></description><pubDate>Tue, 28 Oct 2025 06:26:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=45729714</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=45729714</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45729714</guid></item><item><title><![CDATA[Show HN: Excalidraw for Sticky Notes]]></title><description><![CDATA[
<p>I got tired of having to manage my sticky notes, and I'm not a huge fan of Google Keep. Stickyflo is how I prefer creating/editing/moving notes around. While this ain't a fancy AI app, it does the job (for me, and hopefully for you too!).</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45645674">https://news.ycombinator.com/item?id=45645674</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 20 Oct 2025 16:21:08 +0000</pubDate><link>https://stickyflo.app/</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=45645674</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45645674</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Integer Programming (1977) [pdf]"]]></title><description><![CDATA[
<p>I've always had the impression that Mathematical programming esp. Mixed integer programming/Integer programming is largely "unknown" outside of core engineering and operations research. It's an excellent framework to solve a whole host of problems that arise in business and elsewhere, which are solved using suboptimal (hah) heuristics instead.<p>Okay, maybe I was a bit harsh, but it definitely doesn't pop up as often as deep learning and statistical machine learning. For those who wish to get deeper into this, I highly recommend Optimization over Integers by Bertsimas and Weismantel.</p>
]]></description><pubDate>Mon, 08 Sep 2025 18:03:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=45171643</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=45171643</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45171643</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Dev Compass – Programming Philosophy Quiz"]]></title><description><![CDATA[
<p>Interesting. Deepseek R1:<p>You prefer elegant, high-level solutions that are intuitive and accessible to other developers. You likely favor functional programming, clear abstractions, and code that reads like prose.<p>Abstract ↔ Concrete: +4 Abstract
 Human ↔ Computer Friendly: +9 Human-Friendly</p>
]]></description><pubDate>Sun, 17 Aug 2025 13:45:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=44931512</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=44931512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44931512</guid></item><item><title><![CDATA[New comment by abhishekbasu in "A (not so) small library for terminal based game development"]]></title><description><![CDATA[
<p>+1 for Pyxel, recently used it for a couple of hours to create a tiny project [1] and loved how intuitive it was.<p>[1] <a href="https://github.com/abhishekbasu/minesweeper">https://github.com/abhishekbasu/minesweeper</a></p>
]]></description><pubDate>Tue, 23 Jul 2024 22:03:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=41051444</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=41051444</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41051444</guid></item><item><title><![CDATA[New comment by abhishekbasu in "Exercise: Minesweeper in 100 lines of Ruby"]]></title><description><![CDATA[
<p>This was fun. I saw a post on Pyxel a couple of days ago, and decided to write mine in Python using it.<p><a href="https://github.com/abhishekbasu/minesweeper">https://github.com/abhishekbasu/minesweeper</a></p>
]]></description><pubDate>Mon, 22 Jul 2024 08:40:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=41032086</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=41032086</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41032086</guid></item><item><title><![CDATA[New comment by abhishekbasu in "UnicodePlots"]]></title><description><![CDATA[
<p>There are [1, 2], and AFAICT they rely on gnuplot [3].<p>[1] <a href="https://github.com/nschloe/termplotlib">https://github.com/nschloe/termplotlib</a>
[2] <a href="https://github.com/dkogan/gnuplotlib">https://github.com/dkogan/gnuplotlib</a>
[3] <a href="http://www.gnuplot.info/" rel="nofollow">http://www.gnuplot.info/</a></p>
]]></description><pubDate>Sun, 09 Apr 2023 20:33:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=35506222</link><dc:creator>abhishekbasu</dc:creator><comments>https://news.ycombinator.com/item?id=35506222</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35506222</guid></item></channel></rss>