<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: calumcl</title><link>https://news.ycombinator.com/user?id=calumcl</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 25 Aug 2026 00:49:16 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=calumcl" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by calumcl in "OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)"]]></title><description><![CDATA[
<p>There was context for neither in your original post and I personally saw a lot of similar takes like the above online - apologies for the misunderstanding. I personally thought it was pretty clear considering the parent link is a link to the API pricing and their public communication on their twitter/blogs were "Subscription usage remains unchanged".</p>
]]></description><pubDate>Mon, 24 Aug 2026 20:52:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49425699</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=49425699</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49425699</guid></item><item><title><![CDATA[New comment by calumcl in "OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)"]]></title><description><![CDATA[
<p>Subscribers were already getting subsidised compute and value compared to the 20-200$ fee, peak cakeism to want more considering the alternative would likely be consumption based pricing for individuals so you "benefit" from OpenAI giving up some of their markup (and heavy users end up SOL).</p>
]]></description><pubDate>Mon, 24 Aug 2026 17:35:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49423260</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=49423260</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49423260</guid></item><item><title><![CDATA[New comment by calumcl in "Stacked PRs are now live on GitHub"]]></title><description><![CDATA[
<p>They've provided a skill with their stacking CLI to provide guidance to any coding agent and the Copilot harness now ships with a pr-stack command to do exactly what you're saying for PR splitting FYI: <a href="https://twitter.com/_JeremyMoseley/status/2082190397107994698" rel="nofollow">https://twitter.com/_JeremyMoseley/status/208219039710799469...</a></p>
]]></description><pubDate>Thu, 30 Jul 2026 23:08:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49116985</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=49116985</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49116985</guid></item><item><title><![CDATA[New comment by calumcl in "Nativ: Run frontier open models locally on your Mac"]]></title><description><![CDATA[
<p>The maintainer works on mlx-vlm so he does have pedigree in the scene, I'm don't know if this is just going to end up as unmaintained slop. I haven't tried this but I would personally just recommend oMLX for a currently more complete and fleshed out package - loads of features, provides the same MLX support and changelogs + commits are actually detailed.</p>
]]></description><pubDate>Mon, 20 Jul 2026 20:47:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=48984678</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=48984678</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48984678</guid></item><item><title><![CDATA[New comment by calumcl in "Annoying and alarming things about OpenCode"]]></title><description><![CDATA[
<p>You could easily just use Pi or even a Codex fork to avoid Opencode as a harness and still pay zero dollars.</p>
]]></description><pubDate>Mon, 20 Jul 2026 13:26:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=48978576</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=48978576</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48978576</guid></item><item><title><![CDATA[New comment by calumcl in "Benchmarking coding agents on Databricks' multi-million line codebase"]]></title><description><![CDATA[
<p>Databricks wouldn't be using a subscription plan though due to the size of their engineering team which is what matters here. Free lunch is over for basically all providers' biz coding plans</p>
]]></description><pubDate>Thu, 09 Jul 2026 14:43:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48846737</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=48846737</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48846737</guid></item><item><title><![CDATA[New comment by calumcl in "Kimi K2.7 Code is generally available in GitHub Copilot"]]></title><description><![CDATA[
<p>> These models are hosted on US-based Azure AI Foundry infrastructure managed by GitHub and Microsoft. Customer prompts and responses are not sent to the original model developers.<p>From your link: <a href="https://docs.github.com/en/copilot/reference/ai-models/model-hosting#moonshot-ai-models:~:text=These%20models%20are%20hosted%20on%20US%2Dbased%20Azure%20AI%20Foundry%20infrastructure%20managed%20by%20GitHub%20and%20Microsoft.%20Customer%20prompts%20and%20responses%20are%20not%20sent%20to%20the%20original%20model%20developers" rel="nofollow">https://docs.github.com/en/copilot/reference/ai-models/model...</a>.</p>
]]></description><pubDate>Thu, 02 Jul 2026 09:59:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=48758962</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=48758962</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48758962</guid></item><item><title><![CDATA[New comment by calumcl in "Job: Head of Stonehenge"]]></title><description><![CDATA[
<p>This is a job for a charity - you're never getting stock + bonuses + competitive pay in a third sector job. UK pay is not near US but this is probably still median SWE pay outside tech roles and London + FAANG + others will pay closer with what you're suggesting with the mentioned bonuses/stock.</p>
]]></description><pubDate>Tue, 09 Jun 2026 14:42:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48461804</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=48461804</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48461804</guid></item><item><title><![CDATA[New comment by calumcl in "Pokémon Team Optimization"]]></title><description><![CDATA[
<p>Red and Blue are the international releases of Gen 1 that came out about 2 years after Red/Green.</p>
]]></description><pubDate>Thu, 01 Jan 2026 19:15:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=46457053</link><dc:creator>calumcl</dc:creator><comments>https://news.ycombinator.com/item?id=46457053</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46457053</guid></item></channel></rss>