<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: rebeccajae</title><link>https://news.ycombinator.com/user?id=rebeccajae</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 25 Jun 2026 02:39:57 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rebeccajae" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rebeccajae in "OpenAI unveils its first custom chip, built by Broadcom"]]></title><description><![CDATA[
<p>It seems technically interesting, but they seem very sparse on details. I don't know if I like the idea of a single unchanging model forever on a chip. How much more expensive would the silicon be if they used rewritable ROM for the weights? Such an arrangement would permit fine-tunes of the model it was designed for, which might minimize concerns about the model becoming outdated.</p>
]]></description><pubDate>Wed, 24 Jun 2026 21:11:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48665696</link><dc:creator>rebeccajae</dc:creator><comments>https://news.ycombinator.com/item?id=48665696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48665696</guid></item><item><title><![CDATA[New comment by rebeccajae in "F3"]]></title><description><![CDATA[
<p>It sounds neat, but feels like it might fall apart with higher-complexity formats. What does an embedded decoder for a PDF look like? I guess since they are tightly-coupled to the file bytes themselves, the author of the file gets to choose what formats make sense, but not all formats have a one-true-decode-step.</p>
]]></description><pubDate>Tue, 23 Jun 2026 17:54:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48648677</link><dc:creator>rebeccajae</dc:creator><comments>https://news.ycombinator.com/item?id=48648677</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48648677</guid></item><item><title><![CDATA[New comment by rebeccajae in "AlphaEvolve: Gemini-powered coding agent scaling impact across fields"]]></title><description><![CDATA[
<p>Most people that I have spoken to that are at Google have complained about the internal Gemini agent and seem to believe it's gotten significantly worse lately. Things like it completely forgetting how to call the tools and eventually giving up having wasted a bunch of time, or the agent completely ignoring code style guidance in an AGENTS.md-esque file.<p>My experience running Gemma 4 locally has been similar: after maybe one or two tool calls it starts making tool calls however it feels like. Just yesterday, I watched it redefine a tool like read_file(start, end) into read_file(start, number_of_bytes) and it refused to even consider that it was wrong.</p>
]]></description><pubDate>Fri, 08 May 2026 19:34:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48067669</link><dc:creator>rebeccajae</dc:creator><comments>https://news.ycombinator.com/item?id=48067669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48067669</guid></item></channel></rss>