<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on AW — notes &amp; thoughts</title><link>https://coffepowered.github.io/tags/llm/</link><description>Recent content in Llm on AW — notes &amp; thoughts</description><generator>Hugo -- gohugo.io</generator><language>it-IT</language><managingEditor>Andrea Ruggerini</managingEditor><webMaster>Andrea Ruggerini</webMaster><lastBuildDate>Sat, 10 May 2025 21:28:43 -0500</lastBuildDate><atom:link href="https://coffepowered.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Drawing a coffee plot, with LLMs ep0</title><link>https://coffepowered.github.io/blogs/coffe/</link><pubDate>Sat, 10 May 2025 21:28:43 -0500</pubDate><guid>https://coffepowered.github.io/blogs/coffe/</guid><description>&lt;h1 id="llm-assisted-work"&gt;LLM-assisted work?&lt;/h1&gt;
&lt;p&gt;Will the LLM take over us? Yes, no. Maybe.&lt;/p&gt;
&lt;p&gt;The only thing I&amp;rsquo;m sure about is that those cool stuff are not able to assess the certainty of text (&amp;ldquo;opinions?&amp;rdquo;) they generate.&lt;/p&gt;
&lt;p&gt;Moreover, In my humanly-limited experience, I have yet to see LLMs to meaningful contribute to any asset, i.e. to add valuable and extensive contribution to non-throaway code. All of this may seem strong, but hey, this does not mean productivity cannot be positively impacted.&lt;/p&gt;</description></item></channel></rss>