[HN Gopher] Agentic pelican on a bicycle
       ___________________________________________________________________
        
       Agentic pelican on a bicycle
        
       Author : todsacerdoti
       Score  : 23 points
       Date   : 2025-11-11 19:40 UTC (3 hours ago)
        
 (HTM) web link (www.robert-glaser.de)
 (TXT) w3m dump (www.robert-glaser.de)
        
       | davesque wrote:
       | I feels like it's a bit hard to take much from this without
       | running this trial many times for each model. Then it would be
       | possible to see if there are consistent themes among each model's
       | solutions. Otherwise, it feels like the specific style of each
       | result could be somewhat random. I didn't see any mention of
       | running multiple trials for each model.
        
       | williamstein wrote:
       | > Some models (looking at you, GPT-5-Codex) seemed to mistake
       | "more complex" for "better."
       | 
       | That's what working with GPT-5-Codex on actual code also feels
       | like.
        
       | lubujackson wrote:
       | What I take from this is that LLMs are somewhat miraculous in
       | generation but terrible at revision. Especially with images, they
       | are very resistant to adjusting initial approaches.
       | 
       | I wonder if there is a consistent way to force structural
       | revisions. I have found Nano Banana particularly terrible at
       | revisions, even something like "change the image dimensions
       | to..." it will confidently claim success but do nothing.
        
         | halflife wrote:
         | I'm not quite sure. I think that adversarial network works
         | pretty well at image generation.
         | 
         | I think that the problem here is that svg is structured
         | information and an image is unstructured blob, and the
         | translation between them requires planning and understanding.
         | Maybe if instead of treating an svg like a raster image in the
         | prompt is wrong. I think that prompting the image like code
         | (which svg basically is) would result in better outputs.
         | 
         | This is just my uninformed opinion.
        
         | pinko wrote:
         | I see this all the time when asking Claude or ChapGPT to
         | produce a single-page two-column PDF summarizing the
         | conclusions of our chat. Literally 99% of the time I get a
         | multi-page unpredictably-formatted mess, even after gently
         | asking over and over for specific fixes to the formatting
         | mistake/s.
         | 
         | And as you say, they cheerfully assert that they've done the
         | job, for real this time, every time.
        
       | sorenjan wrote:
       | It would be interesting to see if they would get better results
       | if they didn't grade their own work. Feed the output to a
       | different model and let that suggest improvements, almost like a
       | GAN.
        
       | ripped_britches wrote:
       | I have tried to do agentic figma in this way but same results:
       | attempt 1 becomes frozen and no forward progress can be made.
        
       | andy99 wrote:
       | This wasn't just "add more details"--it was "make this
       | mechanically coherent."
       | 
       | The overall text doesn't appear to be AI written, making this all
       | the more confusing. Is AI making people write this way now on
       | their own? Or is it actually written by an LLM and just doesn't
       | look like it?
        
       ___________________________________________________________________
       (page generated 2025-11-11 23:00 UTC)