<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: zacksiri</title><link>https://news.ycombinator.com/user?id=zacksiri</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 22 Apr 2026 09:51:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=zacksiri" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by zacksiri in "Show HN: My First iOS App"]]></title><description><![CDATA[
<p>It's a lot more than an LLM, it's backed by database + LLM. Gemini / ChatGPT on it's own believe it or not has hallucinated movies and imdb links.<p>While google can show you results it cannot personalize things for you. With this app you can mark movies as seen and you can ask for "things i haven't seen"<p>or ask it to "pick a movie for me" from a search result, you can tell it which region / streaming service you have and search within things you can actually watch.<p>You can't do any of that with google.<p>There are tons of queries i've tried where google will simply not be able to give me good results.<p>The goal is to have a TvOS app where you can just search across all your streaming options and with a single click open / stream any movies you find. Instead of having to search 10 different streaming apps to something you want to watch.<p>In the example you provided I could not see any streaming options for any of the movies or figure out if it's available in my region. I would have to do multiple other search to figure out where I can watch them. I also cannot see ratings etc...</p>
]]></description><pubDate>Mon, 20 Apr 2026 16:44:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=47836903</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47836903</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47836903</guid></item><item><title><![CDATA[New comment by zacksiri in "Show HN: My First iOS App"]]></title><description><![CDATA[
<p>Well with JustWatch and other service aggregators you cannot search for movies by themes / use natural language. For example:<p>- "Zombie or post apocalyptic movies released in the last 5 years"<p>- "Find me top 10 movies on [insert streaming provider]"<p>- "Can you find me top 10 movies released in the last 5 years I haven't seen"<p>- "Movies that will make me feel like I'm trapped in space"<p>- "Movies that put smart people under pressure"<p>You simply cannot do this with the streaming service aggregators or JustWatch.</p>
]]></description><pubDate>Mon, 20 Apr 2026 16:34:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47836719</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47836719</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47836719</guid></item><item><title><![CDATA[Show HN: My First iOS App]]></title><description><![CDATA[
<p>Honestly I didn't think it would be possible when I started, my background is Elixir / Phoenix / Backend engineering. But thx to Codex the app turned out to be something I'm quite proud of.<p>The app is designed to help you find movies to watch. Give you back control, instead of just taking what the algorithms give you, and you end up scrolling for 30 mins not picking anything just to end up on youtube or tiktok.<p>You can find movies based on your interest, ask it for top 10 lists on specific providers and so on...<p>Do let me know your thoughts. I've personally discovered many gems I never knew existed for example:<p>- Uncut Gems<p>- Awakenings<p>- Wake up Dead Man (Knive's Out)<p>- A Quiet Place I / II<p>- Blackberry<p>- Army of Thieves / Army of the Dead<p>- Infernal Affairs<p>- The Amateur<p>I hope it gives you as much joy as it has given me.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47836412">https://news.ycombinator.com/item?id=47836412</a></p>
<p>Points: 2</p>
<p># Comments: 4</p>
]]></description><pubDate>Mon, 20 Apr 2026 16:16:15 +0000</pubDate><link>https://apps.apple.com/us/app/memovee/id6759630955</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47836412</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47836412</guid></item><item><title><![CDATA[New comment by zacksiri in "US and Iran agree to provisional ceasefire"]]></title><description><![CDATA[
<p>I hope that one day humanity learns that in war there are no winners. We're all just brothers and sisters born on different corners of the planet. We share the same home.<p>I hope that we stop attacking one another and find peace and work together as a race to overcome our challenges.</p>
]]></description><pubDate>Wed, 08 Apr 2026 08:25:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=47687065</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47687065</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47687065</guid></item><item><title><![CDATA[The Spectrum of Intelligence]]></title><description><![CDATA[
<p>Article URL: <a href="https://upmaru.com/blog/the-spectrum-of-intelligence">https://upmaru.com/blog/the-spectrum-of-intelligence</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47435215">https://news.ycombinator.com/item?id=47435215</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 19 Mar 2026 05:10:50 +0000</pubDate><link>https://upmaru.com/blog/the-spectrum-of-intelligence</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47435215</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47435215</guid></item><item><title><![CDATA[New comment by zacksiri in "Mistral Small 4"]]></title><description><![CDATA[
<p>It's ok, it's not the best. There are models that do better, I'd use it for some basic tasks but not actual complex tasks like query generation and retrieval.</p>
]]></description><pubDate>Tue, 17 Mar 2026 07:49:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47409730</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47409730</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47409730</guid></item><item><title><![CDATA[New comment by zacksiri in "Mistral Small 4"]]></title><description><![CDATA[
<p>I tested the model in an agentic workflow. Here is the report:<p><a href="https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026/mistral-small-4" rel="nofollow">https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1...</a></p>
]]></description><pubDate>Tue, 17 Mar 2026 05:19:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47408944</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47408944</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47408944</guid></item><item><title><![CDATA[New comment by zacksiri in "Nvidia Nemotron 3 Super"]]></title><description><![CDATA[
<p>I tested this model in an agentic workflow, it failed at some very basic tasks:<p><a href="https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026/nemotron-3-super-120b" rel="nofollow">https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1...</a></p>
]]></description><pubDate>Mon, 16 Mar 2026 08:07:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47396260</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47396260</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47396260</guid></item><item><title><![CDATA[New comment by zacksiri in "Gemini 3.1 Flash-Lite: Built for intelligence at scale"]]></title><description><![CDATA[
<p>Yes, my workflows use caching intensively. It's the only way to keep things fast / economical.</p>
]]></description><pubDate>Tue, 03 Mar 2026 17:32:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=47235782</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47235782</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47235782</guid></item><item><title><![CDATA[New comment by zacksiri in "Gemini 3.1 Flash-Lite: Built for intelligence at scale"]]></title><description><![CDATA[
<p>This is going to be a fun one to play with. I've been conducting tests on various models for my agentic workflow.<p>I was just wishing they would make a new flash-lite model, these things are so fast. Unfortunately 2.5-flash and therefore 2.5-flash-lite failed some of my agentic workflows.<p>If 3.1-flash-lite can do the job, this solves basically all latency issues for agentic workflows.<p>I publish my benchmarks here in case anyone is interested:<p><a href="https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026" rel="nofollow">https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1...</a><p>P.S: The pricing bump is quiet significant, but still stomachable if it performs well. It is significant though.</p>
]]></description><pubDate>Tue, 03 Mar 2026 17:07:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=47235401</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47235401</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47235401</guid></item><item><title><![CDATA[Many LLMs Struggle in Real Agent Workflows]]></title><description><![CDATA[
<p>Article URL: <a href="https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026/">https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47167490">https://news.ycombinator.com/item?id=47167490</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 26 Feb 2026 15:36:21 +0000</pubDate><link>https://upmaru.com/llm-tests/simple-tama-agentic-workflow-q1-2026/</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47167490</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47167490</guid></item><item><title><![CDATA[Retrieval Is Not Intelligence]]></title><description><![CDATA[
<p>Article URL: <a href="https://upmaru.com/blog/intelligence-is-an-architecture-problem/">https://upmaru.com/blog/intelligence-is-an-architecture-problem/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47035424">https://news.ycombinator.com/item?id=47035424</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 16 Feb 2026 14:29:26 +0000</pubDate><link>https://upmaru.com/blog/intelligence-is-an-architecture-problem/</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=47035424</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47035424</guid></item><item><title><![CDATA[New comment by zacksiri in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Just released API Access for my agentic movie search product. So companies can build smart search into their streaming app / tracker apps:<p>Here is a demo link:<p><a href="https://memovee.com/platform/demo?guest_account_id=019c481b-3bd1-7f27-b3b2-f9b75eb53960" rel="nofollow">https://memovee.com/platform/demo?guest_account_id=019c481b-...</a><p>Try queries like:<p>- "Top 10 movies of 2024, sort by highest rating first"<p>- "Top 10 zombie apocalypse movies"<p>- "Find me some good movies that take place in space, no horrors please"<p>- "Some good movies that will make me appreciate life"<p>- "Find me movies like Bladerunner"<p>Or whatever else you can think of. You can also tell it to "filter out movies with less than 300 votes sort by highest rating first" etc...</p>
]]></description><pubDate>Tue, 10 Feb 2026 15:14:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46960785</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=46960785</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46960785</guid></item><item><title><![CDATA[New comment by zacksiri in "Elasticsearch was never a database"]]></title><description><![CDATA[
<p>I never thought of Elasticsearch as a database and always designed systems around what elasticsearch is supposed to be an index based document store for used with search.<p>I think their API is great and have had amazing results with it. Their recent innovations around quantization (bbq) has been amazing for my use case building an agentic movie database for discovering movies and personalized movie recommendations.<p>There are benefits to not using your database for everything, even if it adds a bit of complexity by introducing another dependency. If the benefits out weigh the cost of complexity reaching for elastic has almost always been worth it for me.</p>
]]></description><pubDate>Sat, 17 Jan 2026 06:01:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=46655714</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=46655714</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46655714</guid></item><item><title><![CDATA[New comment by zacksiri in "Ask HN: Share your personal website"]]></title><description><![CDATA[
<p><a href="https://memovee.com" rel="nofollow">https://memovee.com</a> - Agentic movie database<p><a href="https://zacksiri.dev" rel="nofollow">https://zacksiri.dev</a> - My Blog</p>
]]></description><pubDate>Thu, 15 Jan 2026 01:30:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=46626716</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=46626716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46626716</guid></item><item><title><![CDATA[Show HN: Memovee – An agentic movie database]]></title><description><![CDATA[
<p>Hi HN<p>Memovee is an agentic movie database that lets you explore movies using natural language instead of filters or rigid queries.<p>You can ask things like:<p>- “Movies that take place in someone’s mind”<p>- “Top mystery films on Netflix released in the last 5 years”<p>- “Slow-burn sci-fi movies with strong world-building”<p>Under the hood, this isn’t just an LLM wrapper. Memovee uses a structured movie database and an agent layer that translates natural-language intent into deterministic queries and aggregations, then reflects on the results before responding.<p>The agent implementation used by Memovee is open source:
 <a href="https://github.com/upmaru/memovee-tama" rel="nofollow">https://github.com/upmaru/memovee-tama</a><p>This repository shows how intent parsing, query planning, execution, and result refinement are handled step-by-step, rather than relying on opaque prompt chains.<p>The core engine itself is not open-sourced yet. Memovee is one concrete application built on top of a more general engine whose goal is to make it possible to build systems like this for any enterprise domain — not just movies.<p>Engine project:
 <a href="https://kritama.com" rel="nofollow">https://kritama.com</a><p>This is still early and focused purely on movies (not TV yet). Coverage and regional availability vary, and there’s a lot left to improve — especially around reasoning depth, evals, and edge cases.<p>Happy to answer questions about:<p>- The agent architecture<p>- How natural-language intent is mapped to structured data<p>- Agentic vs deterministic tradeoffs<p>- The path toward a reusable enterprise engine<p>Looking forward to feedback — especially critical ones.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46602932">https://news.ycombinator.com/item?id=46602932</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 13 Jan 2026 16:11:01 +0000</pubDate><link>https://memovee.com/</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=46602932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46602932</guid></item><item><title><![CDATA[New comment by zacksiri in "I can build enterprise software but I can't charge for it"]]></title><description><![CDATA[
<p>You obviously didn't read my comment about someone helping him get out of Iran.<p>IF he's out of Iran, works in a company with a founder or investor he's not violating any laws.</p>
]]></description><pubDate>Wed, 12 Nov 2025 00:55:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=45895099</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=45895099</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45895099</guid></item><item><title><![CDATA[New comment by zacksiri in "I can build enterprise software but I can't charge for it"]]></title><description><![CDATA[
<p>No one is failing to acknowledge that he's in a shitty situation. That's precisely the point of my post. It also doesn't mean he cannot be helped.</p>
]]></description><pubDate>Wed, 12 Nov 2025 00:52:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=45895071</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=45895071</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45895071</guid></item><item><title><![CDATA[New comment by zacksiri in "I can build enterprise software but I can't charge for it"]]></title><description><![CDATA[
<p>I feel for this guy, I really do.<p>I see comments like "is this a request to bypass sanctions" OR "he's iranian"<p>Let's remind ourselves of the following:<p>- First understand that he didn't choose to be born and raised in Iran.<p>- Second people grow up have families become attached to where they're born it's not easy to just 'pick up and leave' moving to a new country is expensive and extremely difficult especially from countries like Iran.<p>- Third he's building something he believes in which is probably better than most people who live in privileged countries who sit around and do nothing.<p>To me this reads like a plea for help.<p>He's built something and showing it to the world, if someone likes it and wants to fund him / get him out of Iran, so he can pursue his dreams AND have the people who help him benefit along with him. I'm sure he'll be all for that.</p>
]]></description><pubDate>Wed, 12 Nov 2025 00:44:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=45894992</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=45894992</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45894992</guid></item><item><title><![CDATA[New comment by zacksiri in "Ask HN: What Are You Working On? (Nov 2025)"]]></title><description><![CDATA[
<p>Been building an agentic movie database. <a href="https://memovee.com" rel="nofollow">https://memovee.com</a> already in private testing.<p>The code for the agent is here <a href="https://github.com/upmaru/memovee-tama" rel="nofollow">https://github.com/upmaru/memovee-tama</a></p>
]]></description><pubDate>Mon, 10 Nov 2025 03:23:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=45872023</link><dc:creator>zacksiri</dc:creator><comments>https://news.ycombinator.com/item?id=45872023</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45872023</guid></item></channel></rss>