<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: hek2sch</title><link>https://news.ycombinator.com/user?id=hek2sch</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 28 Sep 2026 17:15:02 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hek2sch" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by hek2sch in "Stripe's Knowledge AI Platform"]]></title><description><![CDATA[
<p>I read a buzz word "Knowledge AI Platform" but I did not see any specific feature helpful for knowledge management like verification or transparency. It is more like any generic Agent builder. Maybe it meant to justify building something  internally.</p>
]]></description><pubDate>Wed, 23 Sep 2026 14:52:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=49817095</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=49817095</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49817095</guid></item><item><title><![CDATA[New comment by hek2sch in "A third of Perplexity's citations don't contain the number they're cited for"]]></title><description><![CDATA[
<p>To be honest perplexity does nothing to make sure it's answer are correct let alone the citations. They just look plausible. For anything little bit serious I use nouswise or nblm that sometimes abstain instead of making things up.</p>
]]></description><pubDate>Wed, 02 Sep 2026 16:52:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49539069</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=49539069</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49539069</guid></item><item><title><![CDATA[New comment by hek2sch in "Nouswise Review: AI Research Agent and Thinking Partner"]]></title><description><![CDATA[
<p>I was wondering what the voice agent or engine behind it is. It sounded better than 11labs.</p>
]]></description><pubDate>Fri, 21 Aug 2026 10:36:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=49386176</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=49386176</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49386176</guid></item><item><title><![CDATA[New comment by hek2sch in "What happens when an LLM never sees material beyond fifth grade?"]]></title><description><![CDATA[
<p>This is an active area of research to inject humility into llms in order to create some kind of knowledge boundary. You can look this paper from nouswise <a href="https://arxiv.org/html/2604.17843v1" rel="nofollow">https://arxiv.org/html/2604.17843v1</a> and the product build on top it to try the humility.</p>
]]></description><pubDate>Sun, 16 Aug 2026 08:46:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=49318163</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=49318163</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49318163</guid></item><item><title><![CDATA[Secure, Fast, and Extensible Sandbox Runtime for AI Agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/TencentCloud/CubeSandbox">https://github.com/TencentCloud/CubeSandbox</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49100880">https://news.ycombinator.com/item?id=49100880</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 29 Jul 2026 18:03:10 +0000</pubDate><link>https://github.com/TencentCloud/CubeSandbox</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=49100880</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49100880</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>I use it for personal use. They have 3 plans, 1 free 2 paid.</p>
]]></description><pubDate>Thu, 16 Jul 2026 22:34:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=48941175</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48941175</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48941175</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>It's been sometime I have been using an app called nouswise. I switched right after they added nblm notebooks in Gemini. I knew they cannot stand another app competing with their flagship. But anyway, it do have audio recap and it definitely have way less of "syntactic sugar". I haven't tried but because it's agentic you can ask it to generate a monologue for you. But I assume you should be in deep mode. I so far only used the side bar for this.</p>
]]></description><pubDate>Thu, 16 Jul 2026 18:49:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48938608</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48938608</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48938608</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>How would the right format for you look like? Specially be monologue?</p>
]]></description><pubDate>Thu, 16 Jul 2026 18:26:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=48938269</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48938269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48938269</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>I have several projects with lots sources (800+). I mostly work with webpages, papers and youtube videos. It also supports mcp if you want to connect something.</p>
]]></description><pubDate>Thu, 16 Jul 2026 18:22:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48938219</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48938219</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48938219</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>The backend has changed people experience more hallucinations. You can see their subs.</p>
]]></description><pubDate>Thu, 16 Jul 2026 18:14:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48938127</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48938127</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48938127</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>It's cumbersome to have llm duplicate all quotes and still get good response. Else you get no visibility into your sources.</p>
]]></description><pubDate>Thu, 16 Jul 2026 17:38:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48937670</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48937670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48937670</guid></item><item><title><![CDATA[New comment by hek2sch in "NotebookLM is now Gemini Notebook"]]></title><description><![CDATA[
<p>Best closest I stumble on is nouswise. Lets you contain an agent with even more sources and generate almost all outputs.</p>
]]></description><pubDate>Thu, 16 Jul 2026 17:36:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48937651</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48937651</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48937651</guid></item><item><title><![CDATA[OpenSandbox Universal Sandbox Infrastructure for AI Applications]]></title><description><![CDATA[
<p>Article URL: <a href="https://open-sandbox.ai/">https://open-sandbox.ai/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48874053">https://news.ycombinator.com/item?id=48874053</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 11 Jul 2026 17:45:49 +0000</pubDate><link>https://open-sandbox.ai/</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48874053</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48874053</guid></item><item><title><![CDATA[New comment by hek2sch in "AI OSS tool repo goes archived over night after raising $7.3M Seed"]]></title><description><![CDATA[
<p>Most VCs avoided application layer believing it is too risky with few player would emerge as winner over application layers calling them GPT wrapper (now called Harness) and pouring money into infra layer. Would love to see your opinion about how this thesis would turn out going forward.</p>
]]></description><pubDate>Sat, 13 Jun 2026 12:10:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=48516505</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48516505</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48516505</guid></item><item><title><![CDATA[AI OSS tool repo goes archived over night after raising $7.3M Seed]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/tensorzero/tensorzero">https://github.com/tensorzero/tensorzero</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48516504">https://news.ycombinator.com/item?id=48516504</a></p>
<p>Points: 279</p>
<p># Comments: 175</p>
]]></description><pubDate>Sat, 13 Jun 2026 12:10:47 +0000</pubDate><link>https://github.com/tensorzero/tensorzero</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48516504</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48516504</guid></item><item><title><![CDATA[Learning from Ava:Lessons from Trustworthy AI for Policy and Dev Research]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/2604.17843">https://arxiv.org/abs/2604.17843</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48309525">https://news.ycombinator.com/item?id=48309525</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 28 May 2026 14:33:37 +0000</pubDate><link>https://arxiv.org/abs/2604.17843</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=48309525</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48309525</guid></item><item><title><![CDATA[New comment by hek2sch in "India's top court angry after junior judge cites fake AI-generated orders"]]></title><description><![CDATA[
<p>Isn't just the issue stemming simply from not using the right tool? When the stakes are high and you should be checking details, the right tools are grounded Ai solutions like nouswise and notebooklm and not the general purpose chatbots that almost everyone knows they might hallucinate. I also do believe that this use case is definitely a low hanging fruit to automat a lot of manual work but it comes with new requirements like transparency to help with verifying the responses.</p>
]]></description><pubDate>Tue, 03 Mar 2026 13:39:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47232154</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=47232154</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47232154</guid></item><item><title><![CDATA[New comment by hek2sch in "OpenAI declares 'code red' as Google catches up in AI race"]]></title><description><![CDATA[
<p>Isn't that already nouswise? Nouswise would ground answers based on low level quotes plus you get an api from your projects.</p>
]]></description><pubDate>Tue, 02 Dec 2025 17:53:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=46124130</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=46124130</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46124130</guid></item><item><title><![CDATA[This Jet Engine Uses No Fuel – Only Microwaves and Air, According to Researchers]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.slashgear.com/2005698/microwave-plasma-jet-engine-no-fossil-fuel/">https://www.slashgear.com/2005698/microwave-plasma-jet-engine-no-fossil-fuel/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45792904">https://news.ycombinator.com/item?id=45792904</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Sun, 02 Nov 2025 19:54:41 +0000</pubDate><link>https://www.slashgear.com/2005698/microwave-plasma-jet-engine-no-fossil-fuel/</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=45792904</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45792904</guid></item><item><title><![CDATA[Chatbots market isn't winner takes all]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.artificialintelligencemadesimple.com/p/what-55-billion-chatbot-visits-actually">https://www.artificialintelligencemadesimple.com/p/what-55-billion-chatbot-visits-actually</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45500200">https://news.ycombinator.com/item?id=45500200</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 07 Oct 2025 07:08:50 +0000</pubDate><link>https://www.artificialintelligencemadesimple.com/p/what-55-billion-chatbot-visits-actually</link><dc:creator>hek2sch</dc:creator><comments>https://news.ycombinator.com/item?id=45500200</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45500200</guid></item></channel></rss>