<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: colin7snyder</title><link>https://news.ycombinator.com/user?id=colin7snyder</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 09 Sep 2026 12:57:27 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=colin7snyder" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Who's Subsidizing Chinese AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.chinese-ai-report.com/">https://www.chinese-ai-report.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48966676">https://news.ycombinator.com/item?id=48966676</a></p>
<p>Points: 4</p>
<p># Comments: 7</p>
]]></description><pubDate>Sun, 19 Jul 2026 10:25:56 +0000</pubDate><link>https://www.chinese-ai-report.com/</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48966676</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48966676</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>I don't disagree with you zingar. I think Erdős problems are great for testing a system's capability on genuinely hard math, which has value as a benchmark in itself, and maybe as a stepping stone toward more real-world impact. Your sentiment is well put.<p>To answer your question directly: most Erdős problems don't have practical applications on their own; the value is the techniques and the machine-checked proofs they leave behind. But there's more real world value in solving some of the FrontierMath Open Problems or Millennium Problems. There's a Venn diagram of "hard problems" and "real world impact" for sure.</p>
]]></description><pubDate>Wed, 15 Jul 2026 13:10:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48920337</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48920337</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48920337</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>Thank you for bringing this up pfdietz. No, not defective. The Lean proofs behind both are machine-checked and unchanged. I withdrew them over framing, not correctness.<p>1) For #129 a couple people pointed out that the report was very confusing. And I agree. So I'm currently attempting to improve it.<p>2) For #130, a person pointed it out as being a partial solution. This seems correct, so I'm currently working on making it fully end to end.<p>These are put out as "proposed solutions" for the mathematics community to scrutinize, and the scrutiny worked exactly like it should. Happy to take any feedback and make them better.</p>
]]></description><pubDate>Wed, 15 Jul 2026 11:42:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48919331</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48919331</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48919331</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>thank you very much for catching this. just fixed</p>
]]></description><pubDate>Wed, 15 Jul 2026 10:19:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48918621</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48918621</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48918621</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>I haven't come across this before. I will spend time on comparator. thank you very much for the suggestion.</p>
]]></description><pubDate>Wed, 15 Jul 2026 10:10:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=48918574</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48918574</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48918574</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>Thank you for the questions echelon.<p>1) As far as the AI models go, we used GPT 5.6 Sol, Fable 5, and Gemini-2-embeddings across the system<p>2) Yes, the agents are given bash tools that allows them to interact with the preinstalled mathematics packages/dependencies that are on the VMs<p>3) This was a setup as a relatively quick project without much thought for future contributions, I will spend some time thinking about how i could make it more open.</p>
]]></description><pubDate>Wed, 15 Jul 2026 10:08:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48918554</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48918554</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48918554</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>I haven't played around with Aristotle at all, thanks for bringing it up & (also your codebase, thesisus, is very solid!)</p>
]]></description><pubDate>Wed, 15 Jul 2026 05:47:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916711</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916711</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916711</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>apologies, bad wording/explanation. As addressed in another comment: "Poor wording on my end, thanks for flagging. I pull the OAuth refresh token from each Codex account into a custom broker, which mints short-lived access tokens per request and load-balances across the pool."</p>
]]></description><pubDate>Wed, 15 Jul 2026 05:43:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916694</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916694</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916694</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>yeah, im currently running the system on navier-stokes (making real progress).<p>Unfortunately P vs NP, on the other hand, is going to have to wait for GPT 7</p>
]]></description><pubDate>Wed, 15 Jul 2026 05:42:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916685</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916685</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916685</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>Poor wording on my end, thanks for flagging. I pull the OAuth refresh token from each Codex account into a custom broker, which mints short-lived access tokens per request and load-balances across the pool.</p>
]]></description><pubDate>Wed, 15 Jul 2026 05:39:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916668</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916668</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916668</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>Thank you for the kind words! I agree, it's exciting that we can now build advanced AI systems for solving novel math (but i still love pen & paper too)</p>
]]></description><pubDate>Wed, 15 Jul 2026 03:56:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916118</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916118</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916118</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>This is great feedback (thank you for taking the time), & you especially bring up a fair point on the writeups needing to be more human readable. I'll work on that</p>
]]></description><pubDate>Wed, 15 Jul 2026 03:51:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916084</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916084</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916084</guid></item><item><title><![CDATA[New comment by colin7snyder in "Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel"]]></title><description><![CDATA[
<p>This is a self funded weekend project for me. It's not associated with any employer (:</p>
]]></description><pubDate>Wed, 15 Jul 2026 03:49:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48916067</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48916067</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48916067</guid></item><item><title><![CDATA[Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.starfleetmath.com/">https://www.starfleetmath.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48914646">https://news.ycombinator.com/item?id=48914646</a></p>
<p>Points: 164</p>
<p># Comments: 110</p>
]]></description><pubDate>Wed, 15 Jul 2026 00:15:56 +0000</pubDate><link>https://www.starfleetmath.com/</link><dc:creator>colin7snyder</dc:creator><comments>https://news.ycombinator.com/item?id=48914646</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48914646</guid></item></channel></rss>