[HN Gopher] Effective AI code suggestions: less is more
       ___________________________________________________________________
        
       Effective AI code suggestions: less is more
        
       Author : swyx
       Score  : 44 points
       Date   : 2025-01-29 16:07 UTC (6 hours ago)
        
 (HTM) web link (www.qodo.ai)
 (TXT) w3m dump (www.qodo.ai)
        
       | itamarcode wrote:
       | AI code review will very probably have signal-to-noise problems.
       | It is good to see practical solutions aimed at addressing this. I
       | wonder if fine-tuning models would help - this isn't addressed in
       | the blog.
        
       | archon810 wrote:
       | I'm intrigued by Qodo after discovering then through this blog
       | post.
       | 
       | Does anyone have experience using its free tier, say, with
       | Github?
        
         | gronky_ wrote:
         | we started using it recently at my work. the code changes
         | walkthrough is nice
        
       | esafak wrote:
       | Is there a benchmark for AI code suggestion, or some comparative
       | review? I don't have the time to test them all; I wonder if I
       | could be using a better one?
        
       | intrepidsoldier wrote:
       | So even the LLMs want to keep doing just easy stuff given a
       | choice?
        
         | mring33621 wrote:
         | "the model consistently gravitated toward style-related
         | suggestions"
         | 
         | sounds very similar to many human-attended code reviews
        
           | dietr1ch wrote:
           | I find some stuff really distracting. Sometimes I just get a
           | local copy to get them out of my way as most are trivial to
           | fix, but hard/draining to ignore.
        
       | turnsout wrote:
       | This matches my experience working with LLMs. I've built several
       | applications that require an LLM to consider several factors or
       | "zoom levels," and I have yet to work with a model that can do
       | that in a single shot. Instead, you need to have multiple passes
       | for each area of focus. Rather than "edit this manuscript," you
       | want "find all the typos," then "find all the run-on sentences,"
       | etc.
        
         | GavCo wrote:
         | Interesting. I wonder if this is related to the model
         | architecture and attention mechanism.
         | 
         | The author seems to be implying it could be: "Even a single
         | mention of 'code enhancement suggestions' in our instructions
         | seemed to hijack the model's attention"
        
           | jimminyx wrote:
           | The attention is probably just latching on to strong
           | statistical patterns. Obvious errors create sharp spikes in
           | attention weights, and drown out more subtle signals that can
           | actually matter more
        
         | timbilt wrote:
         | The weirdness of LLMs is that they're so damn good at so many
         | things but then you see these glaring gaps that instantly make
         | them seem dumb. We desperately need benchmarks and evals that
         | test these kinds of hard to pin down cognitive abilities
        
           | turnsout wrote:
           | Absolutely. This is not a new observation, but another thing
           | they struggle with is self-reporting confidence intervals.
           | When I've asked LLMs to classify/tag things along with a
           | confidence metric, the number seems random and has no
           | connection to the quality or difficulty of the
           | classification.
        
       | coldcode wrote:
       | XCode's assistant AI suggestions are 99% ridiculous, often don't
       | make sense, don't compile, or have nothing to do with my project.
       | Every once in a while it suggests a line or so that is fine. The
       | biggest issue is I want code completion and it appends extra
       | items that make no sense at all, requiring that I either
       | backspace a bunch, or have to use a mouse to pick from the menu.
       | I haven't used Copilot or one of the others, so don't know if
       | this is normal or Apple's is just stupid.
        
         | sippeangelo wrote:
         | So not normal. Try Cursor.
        
       ___________________________________________________________________
       (page generated 2025-01-29 23:01 UTC)