<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: sigseg1v</title><link>https://news.ycombinator.com/user?id=sigseg1v</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 20 Nov 2026 07:42:04 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sigseg1v" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by sigseg1v in "GPT‑6.2 Astra and Sol"]]></title><description><![CDATA[
<p>Curious what you cap your context window at? I go between a cap of 150k and 200k context and I don't feel it hallucinates all the time (sample size about 19,000 commits I've had it write)</p>
]]></description><pubDate>Tue, 17 Nov 2026 20:27:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=50537698</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=50537698</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50537698</guid></item><item><title><![CDATA[New comment by sigseg1v in "Why sending notifications is a nightmare for engineers"]]></title><description><![CDATA[
<p>I just finished a notification subsystem redesign in a moderate sized SaaS and this was one of the top requirements from customers.</p>
]]></description><pubDate>Tue, 17 Nov 2026 14:42:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=50532049</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=50532049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50532049</guid></item><item><title><![CDATA[New comment by sigseg1v in "Anthropic's internal AI use, at retail prices, now exceeds its employee pay"]]></title><description><![CDATA[
<p>On the $200* consumer plan, according to "npx ccusage", I'm using $11,000 per month at API rates. Possibly significantly more, because I was previously using the $100 plan so that only reflects about 1 week of the $200 plan.</p>
]]></description><pubDate>Mon, 02 Nov 2026 18:16:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=50341093</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=50341093</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50341093</guid></item><item><title><![CDATA[New comment by sigseg1v in "No Source Code? No Problem"]]></title><description><![CDATA[
<p>Not the OP but I've tried something like this for a couple things. It costs a $100 monthly plan for about 2 weeks or so, so $50 about? (which is equivalent to about $4500 with API pricing, if you were using Claude, or maybe $100 if you are using something with less grossly inflated pricing).</p>
]]></description><pubDate>Sat, 24 Oct 2026 00:55:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=50217363</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=50217363</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50217363</guid></item><item><title><![CDATA[New comment by sigseg1v in "Newgrounds.com – A community of games, music, and art"]]></title><description><![CDATA[
<p>Working at bigcorp for 14 years so far and I struggle to think of a single day where I didn't need to consider algorithmic complexity or efficiency. Do you not write code that fetches things from a database? Do you not need to make tradeoffs between how much data you fetch at once, which fields you load, which things you cache, whether your query joins on the db or materializes things separately, whether you lazy or eager load, whether you are doing a O(1) or O(n^2) lookup and the tradeoffs, whether you can use a db index or not, memory/latency/compute/storage tradeoffs, etc? I feel like in even a simple bigcorp SAAS you need to consider this stuff daily.</p>
]]></description><pubDate>Sat, 03 Oct 2026 21:47:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49948110</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49948110</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49948110</guid></item><item><title><![CDATA[New comment by sigseg1v in "Gemini 4 Argon"]]></title><description><![CDATA[
<p>I find this discussion interesting. I've had huge increases in accuracy and huge reductions in token usage by capping my Claude models at 200k instead of 1M. I find 1M unusable and wasteful and feel that 200k should be the default. This also makes sense given that the whole reason people use "Ralph loops" is to keep the context window small for all tasks to get better results. Of course, clearing it yourself and manually managing it is better, but if I have 8 projects going in different terminal tabs I'm not watching any one of them that closely to effectively do that.<p>What are people using 1M context window for?</p>
]]></description><pubDate>Fri, 02 Oct 2026 15:22:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=49934546</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49934546</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49934546</guid></item><item><title><![CDATA[New comment by sigseg1v in "Claude Cowork and chat are now one Claude"]]></title><description><![CDATA[
<p>Claude Design is good at making a bunch of UI pages in a single design look consistent, and it's better at making an initial starting UI than just asking Claude Code. Think of it like Anthropic's version of Figma. It honestly works pretty good and I use it often and feel that it saved me a lot of time. It's pretty token heavy though.</p>
]]></description><pubDate>Thu, 17 Sep 2026 14:34:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=49741413</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49741413</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49741413</guid></item><item><title><![CDATA[New comment by sigseg1v in "Fuck it, make it anyway"]]></title><description><![CDATA[
<p>Why would you stop learning new things? 
I lead a team of developers as part of my current role, reviewing and approving what they work on (in addition to doing development and architecture design as well) and from my experience, the difference in someone who has spent time building up their skills in how to do agentic development with AI is so insane. One person can build more than an entire team in some cases, while maintaining quality and needing little to no feedback, yet others using the same AI tools struggle to get anything done. How is this not a skill issue and why would one conclude that you need to stop learning if this is the case?</p>
]]></description><pubDate>Sat, 12 Sep 2026 20:02:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49676626</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49676626</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49676626</guid></item><item><title><![CDATA[New comment by sigseg1v in "Fuck it, make it anyway"]]></title><description><![CDATA[
<p>That take is pretty disingenuous and it makes it hard to take an argument seriously. Who are you to say they did nothing? If someone uses an AI agent to distribute tasks to it like a tech architect does to a team of developers by teaching what to do, and assigning to whom should do it, with examples and instructions, and then reviews the output, offers feedback, and iterates for a few weeks until something is complete, how is that not doing anything? What exactly are you proposing they did for those couple of weeks? Should I imagine that all architects have done nothing their entire life?<p>Are developers that use a "high level" language like C++ also doing nothing because the machine did all the work of compiling to assembly and machine code for them? Nothing to celebrate and no honor?</p>
]]></description><pubDate>Sat, 12 Sep 2026 19:16:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49676095</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49676095</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49676095</guid></item><item><title><![CDATA[New comment by sigseg1v in "ChatGPT Images 2.5"]]></title><description><![CDATA[
<p>With this logic, what is the point to read a book about false events that did not happen? Can we please stop attacking everyone's version of fun or what makes them happy just because it isn't exactly what we like?</p>
]]></description><pubDate>Wed, 09 Sep 2026 14:33:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49627305</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49627305</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49627305</guid></item><item><title><![CDATA[New comment by sigseg1v in "NetBSD 9.5 released and EOL for NetBSD-9"]]></title><description><![CDATA[
<p>Totally inaccurate comparison. Garbage dumped on the side of the road is still garbage. It's more like if someone dumped lab-grown diamonds on the side of the road that are virtually indistinguishable from mined diamonds. Someone would be happy to take them and none the wiser.</p>
]]></description><pubDate>Sun, 06 Sep 2026 20:04:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49590324</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49590324</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49590324</guid></item><item><title><![CDATA[New comment by sigseg1v in "AI handles incidents, engineers lose touch with their systems"]]></title><description><![CDATA[
<p>But this is leaving out the part where the developers that clean up or rewrite... will do it using LLMs.<p>Have you tried refactoring or porting codebases larger than a million lines of code pre-gen-AI and again post-gen-AI? It's night and day difference. One would be insane to schedule a team on 8 months worth of grunt work porting from one language or framework to another which can now be done by 1 person in 4 weeks.<p>Of course the person driving it has to tell it exactly what to do and has to have the requisite knowledge to understand how to effectively structure or fix the software. Maybe new developers don't build this skill so easily anymore. But I don't see why a strong developers skills would atrophy in this case though unless they just never use their knowledge and never give instructions to the AI.<p>To developers speaking of skill atrophy: are you still making sure that when using LLMs you are actively exercising skills like system design, debugging, reviewing for clean code and just in general doing effective code review? If you are doing that, why do you feel skill atrophy? And if you aren't doing it, why not? What about LLMs prevents us from exercising these skills?</p>
]]></description><pubDate>Sat, 05 Sep 2026 12:52:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=49576057</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49576057</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49576057</guid></item><item><title><![CDATA[New comment by sigseg1v in "GPT-6 Astra"]]></title><description><![CDATA[
<p>Every piece of software you have interacted with that's run by a company and has been updated within the last 6 months? You'd be hard pressed to find a company not using AI to develop software.</p>
]]></description><pubDate>Fri, 04 Sep 2026 07:52:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=49561789</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49561789</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49561789</guid></item><item><title><![CDATA[New comment by sigseg1v in "Pre-Release of Polars 2.0"]]></title><description><![CDATA[
<p>Do people actually use languages where it doesn't do any compile time checks on the API in 2026? Why would developers put up with the lack of that. I'm not in this ecosystem but what you are describing sounds like the bare minimum to me that should be table stakes.</p>
]]></description><pubDate>Thu, 03 Sep 2026 14:15:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49550203</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49550203</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49550203</guid></item><item><title><![CDATA[New comment by sigseg1v in "Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why"]]></title><description><![CDATA[
<p>Take a 2 million line of code repo and ask it to convert from programming language A to B and statically verify every logic flow with an AST for each lang, and then get it to write a test harness that hits 100% code coverage, screenshots every major state and compares screenshots for each state between the old and new. Request it uses an agent team with up to 20 agents. You will use that in a few hours easily.</p>
]]></description><pubDate>Fri, 28 Aug 2026 13:33:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49478223</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49478223</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49478223</guid></item><item><title><![CDATA[New comment by sigseg1v in "Logging Back into Facebook"]]></title><description><![CDATA[
<p>I'm surprised that the story in question didn't result in the person being attacked for daring to use Gen AI.<p>The bubble of contacts I have on Facebook seems hell bent on "educating" everyone that all AI is harmful and that anyone who uses AI, be it someone who has never wrote trying to make a poorly done book, or be it a professional using it for red teaming, is horribly, horribly uninformed and lazy and needs to be educated.<p>They have a 2 years out of date mental model of what AI is capable of and they link you things about how it has trouble counting the r's in strawberry or their other common one is water usage. If you point out that they are grossly misinformed, that AI is capable of massive increases in happiness and that now I have more time to spend with my kid even though I have a busy job, and that 1/15th the water usage of residential lawn watering is a lot of water, but it's still 1/15th of what they use on their lawn... they double down and are incapable of resolving their internal conflict. They continue to use the AI generated platform to post messages going through AI algorithms to "educate" you about AI. I don't know why I still log into Facebook.</p>
]]></description><pubDate>Sat, 22 Aug 2026 15:30:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=49400769</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49400769</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49400769</guid></item><item><title><![CDATA[New comment by sigseg1v in "Ask HN: GitHub employees what's going on? Why?"]]></title><description><![CDATA[
<p>Claude has 1 to 2 nines of uptime if you check their uptime history on their site. And I'll note that their definition of up is... generous. Plenty of times I encounter it saying no issues when there are abundant service issues.</p>
]]></description><pubDate>Wed, 19 Aug 2026 07:32:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=49358184</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49358184</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49358184</guid></item><item><title><![CDATA[New comment by sigseg1v in "Generative "AI": The Guitar Hero of Creativity"]]></title><description><![CDATA[
<p>One could also make hotdogs and eat them without developing any skill as a chef, but it's unlikely there would be thousands of blog posts complaining about the downsides of microwaved hotdogs every week.</p>
]]></description><pubDate>Fri, 07 Aug 2026 14:04:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=49210626</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49210626</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49210626</guid></item><item><title><![CDATA[New comment by sigseg1v in "Humans missed 1 in 3 threats approving AI agent commands across 40k game runs"]]></title><description><![CDATA[
<p>If there is an objectively correct right or wrong answer for a given command, why even ask? In that case there should be a configuration page where the user sets up if they want commonly used credentials to be accessible or not, and then there's no prompts.</p>
]]></description><pubDate>Thu, 06 Aug 2026 14:07:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49196912</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49196912</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49196912</guid></item><item><title><![CDATA[New comment by sigseg1v in "Xbox goes down. You can't play games you own on disc"]]></title><description><![CDATA[
<p>The Windows updates have become so unreliable and broken so many laptops that my org switched to Linux and it's been smooth sailing ever since. Can't believe the amount of frustration we put up with using Windows for so long.<p>Maybe for a non tech company yes they cannot navigate anything better due to user expectations, but in my experience those companies usually have support for Mac and at this point I'd rather have that if forced to choose between it and Windows.</p>
]]></description><pubDate>Wed, 05 Aug 2026 12:44:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=49182068</link><dc:creator>sigseg1v</dc:creator><comments>https://news.ycombinator.com/item?id=49182068</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49182068</guid></item></channel></rss>