All Forums  Visual Assist  Technical Support  New VA Intelligence

You must be registered to post a reply.
Click here to register.

Screensize: 640 x 480 800 x 600 1024 x 768 1280 x 1024 UserName: Password: Format: Font Andale Mono Arial Arial Black Book Antiqua Century Gothic Comic Sans MS Courier New Georgia Impact Lucida Console Script MT Bold Stencil Tahoma Times New Roman Trebuchet MS Verdana   Size 1 2 3 4 5 6   Color Black Blue Brown Green Red Violet Yellow Message: Forum code is on. Html is off. [quote][i]Originally posted by Christof Schardt[/i] [br]I gave it a first try today. I selected a 100-line function (part of a JSON parser) and asked it to flag any problematic code and annotate it inline. It took 2.5 minutes to come back with a single finding: that NULL should be replaced with nullptr. For comparison, I pasted the same code into the Claude chat window (via Mammouth), and within 2�3 seconds I had a well-structured list of 5 issues ranging from minor to serious, clearly explained and neatly presented. [b]Problem 1: The performance is unacceptable. Problem 2: The quality of VA's AI is nowhere near that of an external AI.[/b] The supposed benefit of a seamless, integrated workflow doesn't hold up if the underlying results are this far behind and take this much time. Am I expecting too much from VA's built-in AI, or is this a known limitation? Would it make sense, if in addition to the local model an interface to some user defined external LLM would be provided (for people who don't care about locality)? [/quote]   Check to include your profile signature. Check to subscribe to this topic.