<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: gaflo</title><link>https://news.ycombinator.com/user?id=gaflo</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 13 Jun 2026 00:49:10 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=gaflo" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by gaflo in "The newest Instagram “exploit” is the goofiest I've seen"]]></title><description><![CDATA[
<p>Is there any credible primary source for this exploit being real?</p>
]]></description><pubDate>Mon, 01 Jun 2026 17:17:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48359760</link><dc:creator>gaflo</dc:creator><comments>https://news.ycombinator.com/item?id=48359760</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48359760</guid></item><item><title><![CDATA[New comment by gaflo in "Claude Opus 4.8"]]></title><description><![CDATA[
<p>If you upgrade your 8 year old phone the many incremental upgrades will be very noticeable. From my personal experience the LLM space is also moving at a faster pace than the phone industry at the moment, but at least from a financial perspective I would expect it to slow down sooner rather than later.</p>
]]></description><pubDate>Fri, 29 May 2026 01:41:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48317935</link><dc:creator>gaflo</dc:creator><comments>https://news.ycombinator.com/item?id=48317935</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48317935</guid></item><item><title><![CDATA[New comment by gaflo in "GPT-5.5 Price Increase: What It Costs"]]></title><description><![CDATA[
<p>What kind of data are you interpreting? Do you mean document extraction from different languages? I have only used GPT5.5 for agentic coding, which did get significantly better from my experience, although that does align with your conjecture of their focus being on improving this. I haven't noticed a regression when it comes to interacting with it in different languages though (specifically German and Russian). I have done data extraction from documents in different languages, but only with locally hosted LLMs (mainly Qwen3.5-397b) as I cannot legally use cloud-based solutions. My local solution was more than sufficient, so I would be surprised if a frontier model would fail at that.</p>
]]></description><pubDate>Mon, 11 May 2026 08:09:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48092325</link><dc:creator>gaflo</dc:creator><comments>https://news.ycombinator.com/item?id=48092325</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48092325</guid></item><item><title><![CDATA[New comment by gaflo in "GPT-5.5 Price Increase: What It Costs"]]></title><description><![CDATA[
<p>Can you elaborate what kind of system you built? I'm curious what specific prompts are getting worse responses with the newer models.</p>
]]></description><pubDate>Fri, 08 May 2026 20:03:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48068014</link><dc:creator>gaflo</dc:creator><comments>https://news.ycombinator.com/item?id=48068014</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48068014</guid></item></channel></rss>