<html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=utf-8"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
@font-face
{font-family:"EB Garamond";}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:12.0pt;
font-family:"Aptos",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
pre
{mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0in;
margin-bottom:.0001pt;
font-size:10.0pt;
font-family:"Courier New";}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-priority:99;
mso-style-link:"HTML Preformatted";
font-family:"Consolas",serif;}
span.EmailStyle21
{mso-style-type:personal-compose;
font-family:"Aptos",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style></head><body lang=EN-US link=blue vlink=purple style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal><span style='font-size:11.0pt'>I think LLMs companies will benefit by developing datasets for reinforcement learning training based on the behavior of modern tools like compilers (and executables), theorem provers, and symbolic math packages. Some progress can be made with multi-agent conversations and huge context windows, but there needs to be learning – active feedback into the neural net. I’m not sure when programming will not be a thing. For me, software development is more about integration and understanding what components are intended to versus what they really do. But a lot of programmers (or modelers) are write-only type of people. Writing code or conceptualizing models I think will not be a useful skill in a few years. LLMs like Claude I think are already better than most people at rationalizing unseen code and suggesting changes. They need more deep reasoning, though. <o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt'><o:p> </o:p></span></p><div><div style='border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0in 0in 0in'><p class=MsoNormal><b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span style='font-size:11.0pt;font-family:"Calibri",sans-serif'> Friam <friam-bounces@redfish.com> <b>On Behalf Of </b>Pietro Terna<br><b>Sent:</b> Saturday, November 9, 2024 6:50 AM<br><b>To:</b> friam@redfish.com<br><b>Subject:</b> [FRIAM] Swarm again<o:p></o:p></span></p></div></div><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal><span style='font-size:13.5pt;font-family:"EB Garamond"'> For people who created <a href="http://www.swarm.org">http://www.swarm.org</a> or used it, have a look at <br><a href="https://github.com/openai/swarm/blob/main/README.md">https://github.com/openai/swarm/blob/main/README.md</a><br><br> Two completely different worlds or a unique one?<br><br> Best, Pietro</span><br><br><o:p></o:p></p><pre>-- <o:p></o:p></pre><pre>Democrito, che ’l mondo a caso pone (Inferno, IV, 136)<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>"It is the hallmark of any deep truth that its negation is also a deep truth." Niels Bohr.<o:p></o:p></pre><pre><o:p> </o:p></pre><pre>A <a href="https://terna.to.it/breviArticoli.html">https://terna.to.it/breviArticoli.html</a> riporto dei miei brevi articoli su temi di attualità.<o:p></o:p></pre><pre>Asterischi da Verso Itaca a <a href="https://verso-itaca.it/asterischi-da-verso-itaca/">https://verso-itaca.it/asterischi-da-verso-itaca/</a><o:p></o:p></pre><pre><o:p> </o:p></pre><pre>Home page: <a href="https://terna.to.it">https://terna.to.it</a> Twitter: <a href="https://twitter.com/@pietroterna">https://twitter.com/@pietroterna</a><o:p></o:p></pre><pre>Mastodon: <a href="https://mastodon.uno/@PietroTerna">https://mastodon.uno/@PietroTerna</a><o:p></o:p></pre><pre><o:p> </o:p></pre></div></body></html>