<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: joddystreet</title><link>https://news.ycombinator.com/user?id=joddystreet</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 04:23:33 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=joddystreet" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by joddystreet in "GPT‑6.2 Astra and Sol"]]></title><description><![CDATA[
<p>I am not sure, but seems like Sol 6.2 is dumber (whatever that means) than 6.1.
Have not used Astra yet.
Maybe AGI is so smart it seems dumb, like all the great startup ideas :)</p>
]]></description><pubDate>Wed, 18 Nov 2026 07:58:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=50543173</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50543173</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50543173</guid></item><item><title><![CDATA[Ask HN: Where are you on the spectrum of AI/LLM adoption?]]></title><description><![CDATA[
<p>- Personal user (not using in work)<p>- Auto-complete only<p>- Adopted agents, write specs + reviews code<p>- Adopted agents, write specs, no code review<p>- Adopted agents, no specs, no code review<p>- Moved back from agents to Auto-complete only<p>- Moved away from LLMs altogether</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50527647">https://news.ycombinator.com/item?id=50527647</a></p>
<p>Points: 4</p>
<p># Comments: 7</p>
]]></description><pubDate>Tue, 17 Nov 2026 05:00:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=50527647</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50527647</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50527647</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>1. AI subscriptions- Codex (Pro), Ollama (Max), Copilot (for Zed autocompletes)<p>2. N/A<p>3. Coding harnesses - Codex, Pi. (Switched from claude code)<p>4. Just codex, no agent swarms.
When starting a new module - focused work, one issue, one agent, one project.
For smaller tasks/minor issues - multiple parallel sessions, within codex or pi.<p>5. N/A</p>
]]></description><pubDate>Thu, 05 Nov 2026 15:11:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=50380092</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50380092</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50380092</guid></item><item><title><![CDATA[New comment by joddystreet in "What goes into making an animated film?"]]></title><description><![CDATA[
<p>So are there more such articles “what goes into making <X>”?
that you would recommend?
- eg- games, physical objects, hardware, etc?</p>
]]></description><pubDate>Mon, 26 Oct 2026 04:47:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=50239258</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50239258</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50239258</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: Have you observed this trend of building "internal vibe-coding apps"?"]]></title><description><![CDATA[
<p>Are you building one? What are you building? Why?</p>
]]></description><pubDate>Wed, 21 Oct 2026 04:24:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=50176064</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50176064</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50176064</guid></item><item><title><![CDATA[Ask HN: Have you observed this trend of building "internal vibe-coding apps"?]]></title><description><![CDATA[
<p>Article URL: <a href="https://newsletter.pragmaticengineer.com/p/the-pulse-new-trend-of-building-internal">https://newsletter.pragmaticengineer.com/p/the-pulse-new-trend-of-building-internal</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50176063">https://news.ycombinator.com/item?id=50176063</a></p>
<p>Points: 15</p>
<p># Comments: 18</p>
]]></description><pubDate>Wed, 21 Oct 2026 04:24:54 +0000</pubDate><link>https://newsletter.pragmaticengineer.com/p/the-pulse-new-trend-of-building-internal</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50176063</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50176063</guid></item><item><title><![CDATA[Ask HN: How would you go about domain change and getting a job in the domain?]]></title><description><![CDATA[
<p>I have a couple of years of experience with full-stack development (JS/TS, PY, Java), and I've always wanted dive deep into how databases work and how they are built.<p>With LLMs as a teacher, I have been making steady progress in how systems work and how databases work. I am also gaining experience with C++ and Rust. (I can't just code from memory yet, and have to refer to Google for the syntax and then LLMs to learn a better way).<p>Now, coming to switching domains, I am not sure how to go about applying to DB companies.
Would it be weird to apply for an internship, given I am as good as a recent graduate when it comes to systems programming?
Or, are there better ways to go about making this happen?<p>How would you go about - changing domain + getting a job in the domain? (for me, the domain is database development, but I am open to reading suggestions from anyone who has changed domains in recent times, given, with the LLMs, having experience is becoming more important).</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50041008">https://news.ycombinator.com/item?id=50041008</a></p>
<p>Points: 5</p>
<p># Comments: 5</p>
]]></description><pubDate>Sun, 11 Oct 2026 08:46:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=50041008</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=50041008</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50041008</guid></item><item><title><![CDATA[New comment by joddystreet in "AI-generated posters don’t have to be horrible"]]></title><description><![CDATA[
<p>Horrible is - not caring about what AI created, and just throwing it out there.<p>Not horrible is - caring about the outcome, and using AI to make it possible, irrespective of the skill level.<p>Horrible is - everyone trying to copy paste someone else’s work without caring.<p>I think, human thought + ai built is the “not horrible”, might even be awesome</p>
]]></description><pubDate>Sat, 19 Sep 2026 15:06:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=49767164</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49767164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49767164</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are you working on? (September 2026)"]]></title><description><![CDATA[
<p>[HYBRID]<p>Eylo (a take on Hello) a voice first agent platform, multi-tenant, focused on B2B2C use-cases - <a href="https://github.com/DigiCred-OSS/eylo-os" rel="nofollow">https://github.com/DigiCred-OSS/eylo-os</a><p>It’s a distilled fork of a closed source product that we are offering to our customers.</p>
]]></description><pubDate>Mon, 14 Sep 2026 03:55:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=49691798</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49691798</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49691798</guid></item><item><title><![CDATA[New comment by joddystreet in "A week of using Codex more than Claude"]]></title><description><![CDATA[
<p>One more observation - Claude is better at delegation than Codex.<p>Chatgpt is a better planner.<p>Have a discussion in Chatgpt, have Claude to plan work chunks and have GLM to deliver, Codex to review and fix, delivers an overall a better version.<p>Problem - It’s just too much of a context switching.<p>Solution - I am thinking about a new product, a collaborative workspace where I can run this workflow.</p>
]]></description><pubDate>Sun, 23 Aug 2026 09:36:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=49407358</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49407358</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49407358</guid></item><item><title><![CDATA[New comment by joddystreet in "A week of using Codex more than Claude"]]></title><description><![CDATA[
<p>Your words are definitely a better way to put it</p>
]]></description><pubDate>Sun, 23 Aug 2026 09:31:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=49407329</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49407329</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49407329</guid></item><item><title><![CDATA[New comment by joddystreet in "A week of using Codex more than Claude"]]></title><description><![CDATA[
<p>I have completely moved away from Claude to Codex. OpenAI models are better at following instructions and skill use.<p>Claude generates more code, tries to build things that are not planned or needed, repeats same mistakes over and over.<p>Chatgpt on the other hand just does enough, within a project would not repeat the same mistakes, tries to guess your workflow, so you don’t have to ask it to run the same.<p>If you need more control over your code/projects, if you know what you want to get done, use Codex.<p>If you have no idea what you’re doing and are happy to let LLM drive the thing, use Claude.<p>Codex/Chagpt is for the competent.</p>
]]></description><pubDate>Sun, 23 Aug 2026 06:48:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=49406564</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49406564</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49406564</guid></item><item><title><![CDATA[New comment by joddystreet in "Mojo 1.0"]]></title><description><![CDATA[
<p>a systems language that reads like python is great!<p>python superset would have been perfect.<p>I do hope the language thrives and gets a community.<p>All the best to the modular team.</p>
]]></description><pubDate>Wed, 12 Aug 2026 06:26:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49268531</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49268531</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49268531</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are you working on? (August 2026)"]]></title><description><![CDATA[
<p>Follow up - What have you been curious about lately?<p>- Canvas for Agents<p>- LLMs for learning.<p>| <i>Idea</i>: Don't use LLMs for summarisation.
 | <i>Proof of concept</i> -
<a href="https://www.youtube.com/watch?v=1oF9M5hAazw" rel="nofollow">https://www.youtube.com/watch?v=1oF9M5hAazw</a>
 | <i>Repo</i> - 
<a href="https://github.com/veris-pr/bwaiz" rel="nofollow">https://github.com/veris-pr/bwaiz</a></p>
]]></description><pubDate>Mon, 10 Aug 2026 09:22:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=49241301</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49241301</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49241301</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are you working on? (August 2026)"]]></title><description><![CDATA[
<p>SaaS vendors that manage PII data needs to go through the - security questionnaires, privacy assessments, vendor risk reviews, procurement due diligence, evidence requests - sent by the customer security team.<p>At digicred, we were managing these in google drive and jira, but with 500+ enterprise customers, and their annual vendor reviews, this practice became unmanagable.<p>CAOS is a dedicated workspace that helps us manage these assessments like projects, additionally, CAOS turns the questionnaires into a system of record. Questionnaires become structured, answerable work. Finished answers and your compliance documents become a searchable, citable corpus. The next questionnaire starts from what you already said, with every claim traceable to the document or prior answer it came from.<p>It is self-hosted. Your policies, your answers, and your customers' questionnaires stay on your infrastructure.<p>Recently open-sourced - <a href="https://github.com/DigiCred-OSS/caos-os" rel="nofollow">https://github.com/DigiCred-OSS/caos-os</a></p>
]]></description><pubDate>Mon, 10 Aug 2026 09:00:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=49241155</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=49241155</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49241155</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What Are You Working On? (July 2026)"]]></title><description><![CDATA[
<p>A Web-based, self-hosted database client and editor for teams - <a href="https://github.com/p-raj/collab-sqlc" rel="nofollow">https://github.com/p-raj/collab-sqlc</a><p>Supports
- Postgres
- DynamoDB
- Clickhouse
- Redis<p>Primary idea is to evolve from SQL client to a Database Client, where users would be able to host queries, share queries and the work remains auditable.<p>Previously it was an SQL client, a PopSQL alternative. But I am trying to re-work the architecture so that it can support more databases, and services (query-as-service, query-as-reporting-job, etc).</p>
]]></description><pubDate>Mon, 13 Jul 2026 04:45:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48888029</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=48888029</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48888029</guid></item><item><title><![CDATA[AI Economy from the Bottom Up]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.exponentialview.co/p/the-state-of-the-ai-economy">https://www.exponentialview.co/p/the-state-of-the-ai-economy</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48709080">https://news.ycombinator.com/item?id=48709080</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 28 Jun 2026 16:49:20 +0000</pubDate><link>https://www.exponentialview.co/p/the-state-of-the-ai-economy</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=48709080</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48709080</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are you working on? (June 2026)"]]></title><description><![CDATA[
<p>- Web-based, self-hosted database client (a PopSQL alternative)  - <a href="https://github.com/p-raj/collab-sqlc" rel="nofollow">https://github.com/p-raj/collab-sqlc</a><p>- Loaders/Spinners should be fun - <a href="https://github.com/p-raj/pixi-loader" rel="nofollow">https://github.com/p-raj/pixi-loader</a></p>
]]></description><pubDate>Mon, 15 Jun 2026 08:20:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538198</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=48538198</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538198</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are tools you have made for yourself since the advent of AI?"]]></title><description><![CDATA[
<p>Good point, will update the repo. Though, the comics generated by the local llms all kinda suck.
And, not setting this up for yourself is smart, it kind of fills up the disk pretty fast. All the recordings, local llms, etc.</p>
]]></description><pubDate>Tue, 09 Jun 2026 15:26:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48462374</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=48462374</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48462374</guid></item><item><title><![CDATA[New comment by joddystreet in "Ask HN: What are tools you have made for yourself since the advent of AI?"]]></title><description><![CDATA[
<p>There’s another one I’m planning to start - subtitles for your conference calls. 
It would generate netflix like expressive subtitles such as - “uncomfortable silence ensues”, “looks at a distance”, “playful music in the background” etc.</p>
]]></description><pubDate>Tue, 09 Jun 2026 08:49:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48458438</link><dc:creator>joddystreet</dc:creator><comments>https://news.ycombinator.com/item?id=48458438</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48458438</guid></item></channel></rss>