<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: Jayakumark</title><link>https://news.ycombinator.com/user?id=Jayakumark</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 10 Oct 2026 11:14:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Jayakumark" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Jayakumark in "Show HN: Pinrail – A desktop inbox where coding agents wait for your review"]]></title><description><![CDATA[
<p>This looks great, can this be a claude mod ?</p>
]]></description><pubDate>Wed, 07 Oct 2026 23:49:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50000315</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=50000315</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50000315</guid></item><item><title><![CDATA[New comment by Jayakumark in "ChatGPT Pro 500"]]></title><description><![CDATA[
<p>Could hire real people in India for this cost - Fresh college under grads are paid like $250 per month or less for a month working 9hours x 5.5 to 6 days.<p>Edit: I meant its not worth it just for Dots Personal assistant ,also comparing to previous pricing of $200 - For $500 you got previously 5x more than previous $200 Pro pricing (which was 20x now is 10x). I can have real people who can drive or do physical deliveries etc, just on the delta.</p>
]]></description><pubDate>Tue, 29 Sep 2026 18:19:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=49897994</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=49897994</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49897994</guid></item><item><title><![CDATA[New comment by Jayakumark in "LLM-Integrated Multivariable Calculus Course"]]></title><description><![CDATA[
<p>Good, is there calc 1 and calc 2 or should we ask llm ?</p>
]]></description><pubDate>Sun, 19 Jul 2026 04:05:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48964880</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48964880</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48964880</guid></item><item><title><![CDATA[New comment by Jayakumark in "Show HN: FableCut – A browser video editor AI agents can drive (zero deps)"]]></title><description><![CDATA[
<p>A demo video would be good.</p>
]]></description><pubDate>Thu, 09 Jul 2026 13:36:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48845630</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48845630</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48845630</guid></item><item><title><![CDATA[New comment by Jayakumark in "Show HN: Claw Patrol, a security firewall for agents"]]></title><description><![CDATA[
<p>How will credentials be injected via Gateway for each user ? If we have 5 users with one gateway, how it knows whose github credential to inject ?</p>
]]></description><pubDate>Thu, 11 Jun 2026 17:37:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48493610</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48493610</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48493610</guid></item><item><title><![CDATA[New comment by Jayakumark in "Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks"]]></title><description><![CDATA[
<p>Probably in same league <a href="https://github.com/Doorman11991/smallcode" rel="nofollow">https://github.com/Doorman11991/smallcode</a></p>
]]></description><pubDate>Wed, 20 May 2026 06:29:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48203854</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48203854</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48203854</guid></item><item><title><![CDATA[New comment by Jayakumark in "Google I/O"]]></title><description><![CDATA[
<p>The reason they named it as AntiGravIty was based on this. The cli command to launch it is agi</p>
]]></description><pubDate>Tue, 19 May 2026 18:49:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48197577</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48197577</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48197577</guid></item><item><title><![CDATA[New comment by Jayakumark in "Apple Silicon costs more than OpenRouter"]]></title><description><![CDATA[
<p>OP is comparing against Gemma everywhere but concludes paying Anthropic make more sense. Anthropic is $15 per million output token which is 30-35x more expensive even in openrouter .<p>This is like comparing e-bike at home with e-bike rental and concluding therefore we need to rent Toyota since it can go at similar speeds. Getting tired of bad posts getting much attention .</p>
]]></description><pubDate>Sun, 17 May 2026 13:26:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48168745</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=48168745</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48168745</guid></item><item><title><![CDATA[New comment by Jayakumark in "GitHub Copilot is moving to usage-based billing"]]></title><description><![CDATA[
<p>Does this mean you can only prompt "Hello" every morning for a month with Opus 4.7 ?</p>
]]></description><pubDate>Mon, 27 Apr 2026 17:11:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=47924356</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47924356</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47924356</guid></item><item><title><![CDATA[New comment by Jayakumark in "Show HN: Agent Vault – Open-source credential proxy and vault for agents"]]></title><description><![CDATA[
<p>How is it different from Onecli ? And does it do credential stripping ? Will it support access SDK from Bitwarden and integrate with infiscal ?</p>
]]></description><pubDate>Thu, 23 Apr 2026 23:29:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47883597</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47883597</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47883597</guid></item><item><title><![CDATA[New comment by Jayakumark in "Gemini Enterprise Agent Platform, powering the next wave of agents"]]></title><description><![CDATA[
<p>The word agent is used 142 times in this single blog post, They are going overboard.</p>
]]></description><pubDate>Wed, 22 Apr 2026 20:08:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47868625</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47868625</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47868625</guid></item><item><title><![CDATA[New comment by Jayakumark in "Workspace Agents in ChatGPT"]]></title><description><![CDATA[
<p>Looks like ChatGPTs answer to claude managed agents, but using existing ChatGPT Business subscription and not API Keys. With one Caveat , it needs to be invoked from ChatGPT or Slack does not support invoking from APIs, so cannot embed it. Also google launched agent cli today to build own one and integrate with Gemini enterprise <a href="https://developers.googleblog.com/agents-cli-in-agent-platform-create-to-production-in-one-cli/" rel="nofollow">https://developers.googleblog.com/agents-cli-in-agent-platfo...</a></p>
]]></description><pubDate>Wed, 22 Apr 2026 18:54:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47867718</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47867718</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47867718</guid></item><item><title><![CDATA[New comment by Jayakumark in "Workspace Agents in ChatGPT"]]></title><description><![CDATA[
<p>In demo videos, it shows Memory under Files, so i assume it holds learnings and shared context.</p>
]]></description><pubDate>Wed, 22 Apr 2026 18:51:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47867680</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47867680</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47867680</guid></item><item><title><![CDATA[New comment by Jayakumark in "Show HN: Broccoli, one shot coding agent on the cloud"]]></title><description><![CDATA[
<p>Thanks for making it open source, Jira Support would be good</p>
]]></description><pubDate>Wed, 22 Apr 2026 17:05:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47866298</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47866298</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47866298</guid></item><item><title><![CDATA[New comment by Jayakumark in "Claude Managed Agents"]]></title><description><![CDATA[
<p>Thanks for considering it. So how are you doing it now ? Who is generating the plan inside of issue ex: <a href="https://github.com/jonwiggins/optio/issues/418" rel="nofollow">https://github.com/jonwiggins/optio/issues/418</a><p>Do you just add the Issue Title like this  "feat: CLI improvements — status dashboard, workflow commands, shell completions" and it generated the plan in issue body and started working on it OR is the plan generated by another ai agent and copied to issue body for pickup by optio ?</p>
]]></description><pubDate>Mon, 13 Apr 2026 14:55:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47752922</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47752922</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47752922</guid></item><item><title><![CDATA[New comment by Jayakumark in "Claude Managed Agents"]]></title><description><![CDATA[
<p>@jawiggins saw your repo it looks like openAI symphony but better as it works across multiple agents and issue trackers and the feedback loop is great . One feature request though - can you add plan mode ? Your issues are so detailed it becomes plan to implement (but I guess your plan mode is currently happening outside of GitHub issues ) but let’s say issue is “implement support for plan mode” there should be back and forth with agent with issue tags pointing to opus max and/or plan mode  - so we can correct agents plan back and forth and once tag is removed it can start implementing or something similar ?</p>
]]></description><pubDate>Thu, 09 Apr 2026 12:50:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47703048</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47703048</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47703048</guid></item><item><title><![CDATA[New comment by Jayakumark in "Your File System Is Already A Graph Database"]]></title><description><![CDATA[
<p>Interesting approach but how do you download Google Docs, XLS and Slack threads etc.. and how is it saved in obsidian, are they all converted to markdown before saving or summarized to extract key topics and saved. What about images ?</p>
]]></description><pubDate>Wed, 08 Apr 2026 17:53:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=47693807</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47693807</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47693807</guid></item><item><title><![CDATA[New comment by Jayakumark in "Professional video editing, right in the browser with WebGPU and WASM"]]></title><description><![CDATA[
<p>great project but non commercial license, makes me not to go near it.</p>
]]></description><pubDate>Sat, 21 Mar 2026 22:55:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47472380</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47472380</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47472380</guid></item><item><title><![CDATA[New comment by Jayakumark in "MCP is dead; long live MCP"]]></title><description><![CDATA[
<p>Can you please share source code for the Resources/Prompts example ?</p>
]]></description><pubDate>Sat, 14 Mar 2026 22:17:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47381856</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=47381856</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47381856</guid></item><item><title><![CDATA[New comment by Jayakumark in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"]]></title><description><![CDATA[
<p>Awesome work, Would be good to have it work with handy.computer. Also are there plans to support streaming ?</p>
]]></description><pubDate>Tue, 10 Feb 2026 03:43:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46955081</link><dc:creator>Jayakumark</dc:creator><comments>https://news.ycombinator.com/item?id=46955081</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46955081</guid></item></channel></rss>