<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: edverma2</title><link>https://news.ycombinator.com/user?id=edverma2</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 23 Jun 2026 01:16:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=edverma2" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by edverma2 in "OpenAI, the US government and Persona built an identity surveillance machine"]]></title><description><![CDATA[
<p>This is a hilarious personal website! Love it. Even better that it's paired with quality content.</p>
]]></description><pubDate>Tue, 24 Feb 2026 19:23:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47141460</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=47141460</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47141460</guid></item><item><title><![CDATA[New comment by edverma2 in "Claude Sonnet 4.6"]]></title><description><![CDATA[
<p>It seems that extra-usage is required to use the 1M context window for Sonnet 4.6. This differs from Sonnet 4.5, which allows usage of the 1M context window with a Max plan.<p>```<p>/model claude-sonnet-4-6[1m]<p>⎿  API error: 429 {"type":"error","error": {"type":"rate_limit_error","message":"Extra usage is required for long context requests."},"request_id":"[redacted]"}<p>```</p>
]]></description><pubDate>Tue, 17 Feb 2026 18:51:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47051407</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=47051407</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47051407</guid></item><item><title><![CDATA[New comment by edverma2 in "Another GitHub outage in the same day"]]></title><description><![CDATA[
<p>I was just looking into this today but it seems pricey. $29/user/month for basic features like codeowners and defining pr approval requirements. Going with Forgejo.</p>
]]></description><pubDate>Mon, 09 Feb 2026 20:09:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=46950436</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=46950436</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46950436</guid></item><item><title><![CDATA[New comment by edverma2 in "GitHub is down again"]]></title><description><![CDATA[
<p>Anyone have alternatives to recommend? We will be switching after this. Already moved to self-hosted action runners and we are early-stage so switching cost is fairly low.</p>
]]></description><pubDate>Mon, 09 Feb 2026 16:39:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=46947358</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=46947358</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46947358</guid></item><item><title><![CDATA[The Integration Race: America's Advantage Will Be Decided on the Factory Floor]]></title><description><![CDATA[
<p>Article URL: <a href="https://metistech.io/blog/the-integration-race">https://metistech.io/blog/the-integration-race</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46890087">https://news.ycombinator.com/item?id=46890087</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 04 Feb 2026 19:00:31 +0000</pubDate><link>https://metistech.io/blog/the-integration-race</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=46890087</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46890087</guid></item><item><title><![CDATA[New comment by edverma2 in "Elevated errors across many models"]]></title><description><![CDATA[
<p>time to go outside</p>
]]></description><pubDate>Sun, 14 Dec 2025 22:20:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46267691</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=46267691</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46267691</guid></item><item><title><![CDATA[Animals could easily be talking to us if we tried]]></title><description><![CDATA[
<p>Article URL: <a href="https://evanverma.com/animals-could-easily-be-talking-to-us-if-we-tried">https://evanverma.com/animals-could-easily-be-talking-to-us-if-we-tried</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45766920">https://news.ycombinator.com/item?id=45766920</a></p>
<p>Points: 13</p>
<p># Comments: 15</p>
]]></description><pubDate>Fri, 31 Oct 2025 00:04:32 +0000</pubDate><link>https://evanverma.com/animals-could-easily-be-talking-to-us-if-we-tried</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45766920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45766920</guid></item><item><title><![CDATA[New comment by edverma2 in "America’s semiconductor boom [video]"]]></title><description><![CDATA[
<p>Does America need to produce the talent or can they import it?</p>
]]></description><pubDate>Fri, 17 Oct 2025 01:59:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=45612662</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45612662</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45612662</guid></item><item><title><![CDATA[New comment by edverma2 in "GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search"]]></title><description><![CDATA[
<p>From GPT-5-Pro with Deep Research selected:<p>> FWIW Deep Research doesn’t run on whatever you pick in the model selector. It’s a separate agent that uses dedicated o‑series research models: full mode runs on o3; after you hit the full‑mode cap it auto‑switches to a lightweight o4‑mini version. The picker governs normal chat (and the pre‑research clarifying Qs), not the research engine itself.</p>
]]></description><pubDate>Sun, 07 Sep 2025 18:42:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=45160988</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45160988</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45160988</guid></item><item><title><![CDATA[New comment by edverma2 in "A staff engineer's journey with Claude Code"]]></title><description><![CDATA[
<p>I built a tool to split up a single PR into multiple nice commits: <a href="https://github.com/edverma/git-smart-squash" rel="nofollow">https://github.com/edverma/git-smart-squash</a></p>
]]></description><pubDate>Tue, 02 Sep 2025 23:36:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=45110509</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45110509</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45110509</guid></item><item><title><![CDATA[RSS is awesome]]></title><description><![CDATA[
<p>Article URL: <a href="https://evanverma.com/rss-is-awesome">https://evanverma.com/rss-is-awesome</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45058024">https://news.ycombinator.com/item?id=45058024</a></p>
<p>Points: 316</p>
<p># Comments: 117</p>
]]></description><pubDate>Thu, 28 Aug 2025 23:04:01 +0000</pubDate><link>https://evanverma.com/rss-is-awesome</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45058024</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45058024</guid></item><item><title><![CDATA[Claude Runs Claude]]></title><description><![CDATA[
<p>Article URL: <a href="https://evanverma.com/claude-runs-claude">https://evanverma.com/claude-runs-claude</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45021722">https://news.ycombinator.com/item?id=45021722</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 26 Aug 2025 02:43:04 +0000</pubDate><link>https://evanverma.com/claude-runs-claude</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=45021722</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45021722</guid></item><item><title><![CDATA[New comment by edverma2 in "Show HN: Ten years of running every day, visualized"]]></title><description><![CDATA[
<p>This is so cool. Congrats on ten years!</p>
]]></description><pubDate>Mon, 14 Jul 2025 02:27:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=44555884</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=44555884</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44555884</guid></item><item><title><![CDATA[New comment by edverma2 in "I scanned all of GitHub's "oops commits" for leaked secrets"]]></title><description><![CDATA[
<p>All devs should run open-source trufflehog as a precommit hook for all repositories on their local system. It’s not a foolproof solution, but it’s a small time investment to get set up and gives me reasonable assurance that I will not accidentally commit a secret. I’m unsure why this is not more widely considered standard practice.</p>
]]></description><pubDate>Thu, 03 Jul 2025 07:48:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=44452644</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=44452644</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44452644</guid></item><item><title><![CDATA[New comment by edverma2 in "Show HN: Tool to Automatically Create Organized Commits for PRs"]]></title><description><![CDATA[
<p>Interesting! I’ve faced the same problem where I have a mega PR and spend a lot of time breaking that up into separate PRs. I agree that what you are suggesting is a different but related problem to what this tool currently solves. I’ll start thinking through how this would look, and I’ll go ahead and make a GitHub issue if you or anyone else wants to start a discussion there.</p>
]]></description><pubDate>Fri, 20 Jun 2025 04:59:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=44324867</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=44324867</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44324867</guid></item><item><title><![CDATA[Show HN: Tool to Automatically Create Organized Commits for PRs]]></title><description><![CDATA[
<p>I've found it helps PR reviewers when they can look through a set of commits with clear messages and logically organized changes. Typically reviewers prefer a larger quantity of smaller changes versus a smaller quantity of larger changes. Sometimes it gets really messy to break up a change into sufficiently small PRs, so thoughtful commits are a great way of further subdividing changes in PRs. It can be pretty time consuming to do this though, so this tool automates the process with the help of AI.<p>The tool sends the diff of your git branch against a base branch to an LLM provider. The LLM provider responds with a set of suggested commits with sensible commit messages, change groupings, and descriptions. When you explicitly accept the proposed changes, the tool re-writes the commit history on your branch to match the LLM's suggestion. Then you can force push your branch to your remote to make it match.<p>The default AI provider is your locally running Ollama server. Cloud providers can be explicitly configured via CLI argument or in a config file, but keeping local models as the default helps to protect against unintentional data sharing. The tool always creates a backup branch in case you need to easily revert in case of changing your mind or an error in commit re-writing. Note that re-writing commit history to a remote branch requires a force push, which is something your team/org will need to be ok with. As long as you are working on a feature branch this is usually fine, but it's always worth checking if you are not sure.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44324457">https://news.ycombinator.com/item?id=44324457</a></p>
<p>Points: 76</p>
<p># Comments: 51</p>
]]></description><pubDate>Fri, 20 Jun 2025 03:22:59 +0000</pubDate><link>https://github.com/edverma/git-smart-squash</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=44324457</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44324457</guid></item><item><title><![CDATA[Show HN: Vibe Coding Security Hook]]></title><description><![CDATA[
<p>This is a simple git pre-commit hook that uses your locally running Ollama instance to scan your commit for secrets, blocking the commit and suggesting a fix if any secrets are found.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43950563">https://news.ycombinator.com/item?id=43950563</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 11 May 2025 01:44:25 +0000</pubDate><link>https://github.com/edverma/vibe-code-security-hook</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=43950563</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43950563</guid></item><item><title><![CDATA[New comment by edverma2 in "Librarians are dangerous"]]></title><description><![CDATA[
<p>Why do people speak online as if the library is a place anyone goes to? I understand some people still go to libraries, but this cannot be considered a commonplace activity like it once was. Librarians do not hold any meaningful position in society because so few people come in contact with them.</p>
]]></description><pubDate>Sat, 19 Apr 2025 18:03:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=43738161</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=43738161</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43738161</guid></item><item><title><![CDATA[Show HN: LLM Writing Feedback Tool]]></title><description><![CDATA[
<p>I wrote this simple rust program to watch a file and give me feedback as I work on it. It’s been really nice and helpful for me so far, so hopefully others can get value from it also.<p>I also posted a brief writeup about it here: <a href="https://evanverma.com/writing-with-claude-watching-my-every-move" rel="nofollow">https://evanverma.com/writing-with-claude-watching-my-every-...</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42768985">https://news.ycombinator.com/item?id=42768985</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 20 Jan 2025 14:20:05 +0000</pubDate><link>https://github.com/edverma/llm-writing-feedback</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=42768985</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42768985</guid></item><item><title><![CDATA[Writing with Claude Watching My Every Move]]></title><description><![CDATA[
<p>Article URL: <a href="https://evanverma.com/writing-with-claude-watching-my-every-move">https://evanverma.com/writing-with-claude-watching-my-every-move</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42762791">https://news.ycombinator.com/item?id=42762791</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 19 Jan 2025 22:38:26 +0000</pubDate><link>https://evanverma.com/writing-with-claude-watching-my-every-move</link><dc:creator>edverma2</dc:creator><comments>https://news.ycombinator.com/item?id=42762791</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42762791</guid></item></channel></rss>