<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: elwebmaster</title><link>https://news.ycombinator.com/user?id=elwebmaster</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 25 Oct 2026 08:03:26 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=elwebmaster" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by elwebmaster in "I turned my unused Kindle into a photo frame with GPT-6 Astra"]]></title><description><![CDATA[
<p>Turning Kindle into photo frame is not exciting, turning phot frame into Kindle would be!</p>
]]></description><pubDate>Tue, 13 Oct 2026 02:44:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=50065920</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=50065920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50065920</guid></item><item><title><![CDATA[New comment by elwebmaster in "One Month Without AI"]]></title><description><![CDATA[
<p>One very unfortunate curse we are stuck with is LLM providers pulling the rug from under us and swapping models with quantized versions during peak demand or on monthly plans. You never know if that's the reason AI starts writing shitty code or it's just the context size that has grown. On top of that there is the queuing mechanism which makes tasks take longer. Sometimes AI is super fast and sometimes a simple task takes 10, 15 or even 20 minutes of "thinking". You may not realize this if you are just using your same subscription but if you switch between providers you can immediately tell. I advise everyone to invest $5 in openrouter, deepseek and qwencode. Just do an experiment and use same model (deepseek-4.1 flash) asking same prompt on same code, then look at the result. Spoiler: you will see trash coming out of openrouter at 1-5 tokens/second, you will see slightly faster and better quality output from qwencloud and when you get to deepseek API where you are paying per token you will not believe this is the same model. Because it isn't.</p>
]]></description><pubDate>Sat, 26 Sep 2026 12:02:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=49855724</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49855724</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49855724</guid></item><item><title><![CDATA[New comment by elwebmaster in "Benchmark: CadQuery vs. OpenSCAD for agentic CAD work"]]></title><description><![CDATA[
<p>Dude, coat hanger joint is broken. The free chatgpt gives openscat file I can just paste and convert to stl. I didn't even measure the diameter of the pipe, apparently those are standard. In 10 minutes I have a new 3d printed part to fix my coat hanger. No CAD UI app subscriptions, not reading CAD books or whatever. That's real life. Rest is in your mind.</p>
]]></description><pubDate>Sun, 13 Sep 2026 01:53:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49679144</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49679144</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49679144</guid></item><item><title><![CDATA[New comment by elwebmaster in "Benchmark: CadQuery vs. OpenSCAD for agentic CAD work"]]></title><description><![CDATA[
<p>People don't have time (or even mental capability / even more time) to learn CAD but they have a task at hand which they want done. If AI can generate a part which is "good enough" for the user at a cost that the user considers reasonable (I.e. zero) then AI gets used. If a part fails thats rarely a concern because these parts are just 3d printed and likely cost single digit cents in filament. User can always print a new one.</p>
]]></description><pubDate>Sat, 12 Sep 2026 21:17:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49677305</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49677305</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49677305</guid></item><item><title><![CDATA[New comment by elwebmaster in "Benchmark: CadQuery vs. OpenSCAD for agentic CAD work"]]></title><description><![CDATA[
<p>With any tool?</p>
]]></description><pubDate>Sat, 12 Sep 2026 20:58:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49677125</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49677125</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49677125</guid></item><item><title><![CDATA[New comment by elwebmaster in "Grok Bot"]]></title><description><![CDATA[
<p>We are doing AI screening. Candidate works with AI for 15 minutes and session is recorded. We review real output not AI generated resume. If candidate can get AI to apply and produce meaningful output then maybe we should hire that candidate. Currently outputs are manually reviewed but easy enought to have AI screen outputs.</p>
]]></description><pubDate>Wed, 12 Aug 2026 02:51:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=49267314</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49267314</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49267314</guid></item><item><title><![CDATA[New comment by elwebmaster in "Ghost Cut – Or why Cut and Paste is broken everywhere"]]></title><description><![CDATA[
<p>Oh if only cut and paste was broken... In Windows and Linux copy and paste itself is broken. Sometimes you copy with mouse, sometimes you copy with keyboard, and if it is a recent version of MS Office likely neither will work. Sometimes you paste with Ctrl+v sometimes with Ctrl+shift+v, sometimes with mouse, sometimes it just won't work. Such a simple operation should have been completely owned by the OS.</p>
]]></description><pubDate>Wed, 22 Jul 2026 23:14:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=49014763</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=49014763</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49014763</guid></item><item><title><![CDATA[New comment by elwebmaster in "A retrospective of my time on the internet"]]></title><description><![CDATA[
<p>Can we bring it back with LoRA? It has a lot of the properties of the original internet: decentralization, slow speeds, and limited access.</p>
]]></description><pubDate>Wed, 01 Jul 2026 16:26:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48749409</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48749409</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48749409</guid></item><item><title><![CDATA[New comment by elwebmaster in "Anthropic says Alibaba illicitly extracted Claude AI model capabilities"]]></title><description><![CDATA[
<p>Nonsense. Many if not all legit Claude users are using Claude Code inside their Cloud servers. How else would you use it anyway? For just local dev? That's so 2000 and late bro.</p>
]]></description><pubDate>Thu, 25 Jun 2026 02:21:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48668057</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48668057</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48668057</guid></item><item><title><![CDATA[New comment by elwebmaster in "Deno Desktop"]]></title><description><![CDATA[
<p>Enough with web trash! Isn't vibe coding enough to build a proper program?</p>
]]></description><pubDate>Tue, 23 Jun 2026 01:01:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48638780</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48638780</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48638780</guid></item><item><title><![CDATA[New comment by elwebmaster in "GLM-5.2 is the new leading open weights model on Artificial Analysis"]]></title><description><![CDATA[
<p>You are not alone. How about GPT 5.5? Does it come close to Fable 5?</p>
]]></description><pubDate>Wed, 17 Jun 2026 11:08:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48568636</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48568636</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48568636</guid></item><item><title><![CDATA[New comment by elwebmaster in "A backdoor in a LinkedIn job offer"]]></title><description><![CDATA[
<p>Why is npm still not blocked by every OS on earth is beyond me. These guys will never learn.</p>
]]></description><pubDate>Mon, 15 Jun 2026 23:21:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48548433</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48548433</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48548433</guid></item><item><title><![CDATA[New comment by elwebmaster in "Age verification for social media, the beginning of the end for a free internet?"]]></title><description><![CDATA[
<p>There is no bona fide desire to solve the problem by the social media companies which are profiting from our kids. As a parent, I can never find the option to enable parental controls on apps like YouTube (especially on TV). This option is easy enough to implement locally without requiring any accounts or OS-level age support. However, clearly the goal is not to protect the children but to enable mass scale surveillance and profit from it.
Even when I manage to enable parental controls by using a dedicated app or account (what nonsense is it that I need to create an account to restrict access!!!) the content being served is dubiously appropriate for the age group, aside from having no value whatsoever other than the intended goal of perpetuating addiction.</p>
]]></description><pubDate>Tue, 02 Jun 2026 11:44:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48368955</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48368955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48368955</guid></item><item><title><![CDATA[New comment by elwebmaster in "GM just laid off IT workers to hire those with stronger AI skills"]]></title><description><![CDATA[
<p>You won't be asked, your tax dollars will just be used to bail them out, either directly or through tariffs. Because democracy.</p>
]]></description><pubDate>Tue, 12 May 2026 00:27:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=48102607</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48102607</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48102607</guid></item><item><title><![CDATA[New comment by elwebmaster in "LLMs Are Not a Higher Level of Abstraction"]]></title><description><![CDATA[
<p>I have done this, alias codex --yolo -p . It's very helpful not having to remember every odd command and its parameters. It's a bit more typing but I type faster than invoke and scan through man pages.</p>
]]></description><pubDate>Mon, 04 May 2026 04:03:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48004495</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=48004495</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48004495</guid></item><item><title><![CDATA[New comment by elwebmaster in "Alberta startup sells no-tech tractors for half price"]]></title><description><![CDATA[
<p>Next up, cars with no-tech! Bring them on.</p>
]]></description><pubDate>Thu, 23 Apr 2026 03:19:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47871952</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=47871952</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47871952</guid></item><item><title><![CDATA[New comment by elwebmaster in "The Vercel breach: OAuth attack exposes risk in platform environment variables"]]></title><description><![CDATA[
<p>Nailed it.</p>
]]></description><pubDate>Wed, 22 Apr 2026 02:34:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47858126</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=47858126</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47858126</guid></item><item><title><![CDATA[New comment by elwebmaster in "The Vercel breach: OAuth attack exposes risk in platform environment variables"]]></title><description><![CDATA[
<p>"The parent platform" yada yada, my parent platform is bare metal, how about that?</p>
]]></description><pubDate>Wed, 22 Apr 2026 02:31:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47858092</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=47858092</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47858092</guid></item><item><title><![CDATA[New comment by elwebmaster in "Backpacks got worse on purpose"]]></title><description><![CDATA[
<p>We always see consumers blamed for choosing price over quality. How about retailers taking the blame for dumbing down or removing product specs? If two items look identical but one costs more than the other how can consumer be blamed for choosing the cheaper ones? Especially in the age of LLMs, it you are building a quality product you need to include a spec sheet of what makes your product better than the competitor. Not dumbed down marketing speak like "lasts longer" but specific details justifying the premium, like "zippers made in Japan" or the stitching density, fabric specifics, etc. Consumers who care can use LLM to understand what it all means and make informed choice. But when the information is hidden consumer will choose the cheapest option.</p>
]]></description><pubDate>Wed, 15 Apr 2026 14:32:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47779556</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=47779556</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47779556</guid></item><item><title><![CDATA[New comment by elwebmaster in "I run multiple $10K MRR companies on a $20/month tech stack"]]></title><description><![CDATA[
<p>Can OP write another article focusing on the revenue side, how to actually bring in $10K MRR, forget about the tech stack, AI can solve that.</p>
]]></description><pubDate>Sun, 12 Apr 2026 19:41:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47743597</link><dc:creator>elwebmaster</dc:creator><comments>https://news.ycombinator.com/item?id=47743597</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47743597</guid></item></channel></rss>