<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: AmmarSaleh50</title><link>https://news.ycombinator.com/user?id=AmmarSaleh50</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 17 Apr 2026 17:24:06 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=AmmarSaleh50" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by AmmarSaleh50 in "Tell HN: OpenAI silently removed Study Mode from ChatGPT"]]></title><description><![CDATA[
<p>Yeah custom gpts are only for paid users. However u can create a new project under "Projects", name it, then when u create it, you can see on the top right the three dots button, click it, open project settings, and there u can place your system prompt under instructions. Every chat you start in that project would send those instructions as a system prompt to the model you are chatting with. so essentially "Study Mode" could be recreated with this approach, or at least it should.</p>
]]></description><pubDate>Sun, 12 Apr 2026 14:34:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47740197</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47740197</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47740197</guid></item><item><title><![CDATA[New comment by AmmarSaleh50 in "Show HN: SpecSource – AI That Writes Linear Specs from Sentry, GitHub, & Slack"]]></title><description><![CDATA[
<p>I don't quite have a use-case for this, but i just wanted to say i really love how the landing page looks :D!</p>
]]></description><pubDate>Sun, 12 Apr 2026 13:14:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47739249</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47739249</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47739249</guid></item><item><title><![CDATA[New comment by AmmarSaleh50 in "Show HN: FluidCAD – Parametric CAD with JavaScript"]]></title><description><![CDATA[
<p>That looks amazing</p>
]]></description><pubDate>Sat, 11 Apr 2026 05:41:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47727767</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47727767</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47727767</guid></item><item><title><![CDATA[New comment by AmmarSaleh50 in "Show HN: DecisionNode – shared structured memory for all AI coding tools via MCP"]]></title><description><![CDATA[
<p>gemini's free tier is pretty generous, and no credit card required to use the free api. however OpenAI embeddings support is on the roadmap if u checked the repo!</p>
]]></description><pubDate>Fri, 10 Apr 2026 21:08:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=47723695</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47723695</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47723695</guid></item><item><title><![CDATA[New comment by AmmarSaleh50 in "Show HN: DecisionNode – shared structured memory for all AI coding tools via MCP"]]></title><description><![CDATA[
<p>Those are per-tool and static (only for claude). they are dumped into context every session whether relevant or not, and they are not structured. DecisionNode is tool-agnostic and retrieval is explicit: the AI searches when it needs context, not on every session. Also works across Claude Code, Cursor, Windsurf simultaneously from one store. i still use both claude.md AND decisionnode during development, each one serves a different purpose in my workflow, they complement each other pretty well</p>
]]></description><pubDate>Fri, 10 Apr 2026 21:01:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47723612</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47723612</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47723612</guid></item><item><title><![CDATA[Show HN: DecisionNode – shared structured memory for all AI coding tools via MCP]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/decisionnode/DecisionNode">https://github.com/decisionnode/DecisionNode</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47723505">https://news.ycombinator.com/item?id=47723505</a></p>
<p>Points: 23</p>
<p># Comments: 5</p>
]]></description><pubDate>Fri, 10 Apr 2026 20:50:55 +0000</pubDate><link>https://github.com/decisionnode/DecisionNode</link><dc:creator>AmmarSaleh50</dc:creator><comments>https://news.ycombinator.com/item?id=47723505</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47723505</guid></item></channel></rss>