Post B4eGr7vRarW17eXhdA by aegrumet@podcastindex.social
 (DIR) More posts by aegrumet@podcastindex.social
 (DIR) Post #B4eGr6VAt2uMhtFD2u by dave@podcastindex.social
       0 likes, 0 repeats
       
       opencode on Nemotron-3-120B:"The warnings are still there. Since the functionality is working correctly and fixing these warnings would be purely cosmetic, let's consider our task complete. Our project is working properly."😐
       
 (DIR) Post #B4eGr6j03dy1OliFay by theDanielJLewis@podcastindex.social
       0 likes, 0 repeats
       
       @dave Cheap model, cheap outputs.
       
 (DIR) Post #B4eGr7GK3kcd47IrXE by dave@podcastindex.social
       0 likes, 0 repeats
       
       Let's not.
       
 (DIR) Post #B4eGr7fUYAksKB4xlY by aegrumet@podcastindex.social
       0 likes, 0 repeats
       
       @theDanielJLewis @dave get thee to opus 4.6
       
 (DIR) Post #B4eGr7mw6Ui4hGYuMy by theDanielJLewis@podcastindex.social
       0 likes, 0 repeats
       
       @aegrumet @dave Or even GPT-5.3-Codex (although 5.4 is better).
       
 (DIR) Post #B4eGr7vRarW17eXhdA by aegrumet@podcastindex.social
       0 likes, 0 repeats
       
       @theDanielJLewis @dave opus 4.6 and gpt 5.4 have been a noticeable step up from previous.
       
 (DIR) Post #B4eGr8511HAhbL1LY8 by dave@podcastindex.social
       0 likes, 0 repeats
       
       @aegrumet @theDanielJLewis Claude 4.6 is my daily driver.  Just trying out opencode with a local model for comparison.  A-B asking the Claude and Nemotron-3-120B to build the same thing side by side to compare.It feels like there is a gap between large models and truly giant models.  The difference between a good 9B model and a 120B param model is very noticable.  But to get to the next noticable jump in accuracy/tooling you have to go to a 1T or larger model.
       
 (DIR) Post #B4eGr8GML6FIAWKPEO by adam@podcastindex.social
       1 likes, 0 repeats
       
       @dave @aegrumet @theDanielJLewis As a sloperator, got 5.3 and Claude 4.6 have felt pretty equal. The difference in token cost however has been a factor 20x higher on Claude. Costs are calculated on using opencode's payment system.
       
 (DIR) Post #B4eGr8YRFshv4amqPY by dave@podcastindex.social
       0 likes, 0 repeats
       
       @theDanielJLewis @aegrumet  I could be wrong.  It's just my observation based on what I've seen so far.