TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

LLM tech comes to Wolfram Language

148 pointsby zyl1nalmost 2 years ago

9 comments

gololalmost 2 years ago
Symbolic AI could never become great because it was missing the connection to the intricacies of the real world that you can only get from data. I think a symbioses of symbolic techniques with LLMs or generally multimodal autoregressive foundation models will lead to our first legit "AGIish" agents. The LLM takes the role of a little gremlin inside the machine that provides the magic sauce, that tiny bit of general intelligence or common sense necessary to connect arbitrary interfaces.
评论 #36537428 未加载
评论 #36532627 未加载
评论 #36535160 未加载
animal_spiritsalmost 2 years ago
This is quite impressive. Especially the auto-correcting and error reporting. I always thought of Mathematica as a cool, but not worth the price technology. This LLM integration into the notebooks is totally increasing the value and making me consider giving it a try.
评论 #36530411 未加载
评论 #36530398 未加载
DesiLurkeralmost 2 years ago
Nice, now we just need to integrate AR headset and we can have proper Tony Stark style dictated &#x27;research laboratory&#x27;.<p>edit: I spoke too soon, it actually has a module to publish AR model object of the design you created. so this could potentially be directly usable with AR glasses.
ilakshalmost 2 years ago
Relies on GPT-4. Maybe there could be a multistage way to get similar automated API usage with smaller open source models?<p>I wonder if it would be possible to train a 7B or 13B model to generate code in just one specific programming language. Train it with example problem input&#x2F; program output pairs. Then train another small model to translate natural language in a specific domain into an input for the coder model. And maybe a third to translate that into a different real programming language.<p>The point of this being that you can use smaller GPU instances and dedicate all of the limited power of each model to narrower domain that may be more tractable for it.
评论 #36538992 未加载
TechBro8615almost 2 years ago
Wow, I just learned about this ARObject thing. You can long press a QR code on an iPhone and see a 3d object in AR. Or without a QR code for example, if you&#x27;re on an iPhone, try following this link [0] and then tapping the body of the page.<p>[0] <a href="https:&#x2F;&#x2F;www.wolframcloud.com&#x2F;obj&#x2F;yanz&#x2F;Base&#x2F;Temp&#x2F;AR&#x2F;201a538b-067d-4965-b012-4a367204b0c9&#x2F;model.usdz" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.wolframcloud.com&#x2F;obj&#x2F;yanz&#x2F;Base&#x2F;Temp&#x2F;AR&#x2F;201a538b-...</a>
villgaxalmost 2 years ago
All I actually want is an LLM which can adhere to a set of rules, like a language spec, library&#x2F;framework code &amp; then help me make stuff rather than hallucination of arbitrary version numbers &amp; staying in an infinite loop of trying every iteration of code by myself in an IDE
mark_l_watsonalmost 2 years ago
I used to subscribe to Wolfram Cloud&#x2F;Desktop. I liked it, but never really loved the language itself.<p>I tried a Chat Notebook on Wolfram Cloud this morning, and asked it to write a script to fetch data from DBPedia and present it. It generated Wolfram Language code, so that was very cool.
Aardwolfalmost 2 years ago
It&#x27;s a bit unclear from this post: is this a locally running LLM or in the cloud and if so whose servers? Does it use an existing service like openai or a completely new model specific to wolfram?
评论 #36532642 未加载
bandramialmost 2 years ago
&quot;Perfect third&quot;?
评论 #36530337 未加载
评论 #36530309 未加载