Agentic pelican on a bicycle
robert-glaser.de
Agentic pelican on a bicycle
1–10 of 77 posts
Re: Agentic pelican on a bicycle
#2I 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.
Re: Agentic pelican on a bicycle
#3> 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.
Re: Agentic pelican on a bicycle
#4What 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.
Re: Agentic pelican on a bicycle
#5It 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.
Re: Agentic pelican on a bicycle
#6What 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.
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.
Re: Agentic pelican on a bicycle
#7I have tried to do agentic figma in this way but same results: attempt 1 becomes frozen and no forward progress can be made.
Re: Agentic pelican on a bicycle
#8What 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.
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.
Re: Agentic pelican on a bicycle
#9 This wasn’t just “add more details”—it was “make this mechanically coherent.”
Re: Agentic pelican on a bicycle
#10What 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.
Tools are still evolving out of the VLM/LLM split [0]. The reason image-to-image tasks are so variable in quality and vastly inferior to text-to-image tasks is because there is an entirely separate model that is trained on transforming an input image into tokens in the LLM's vector space.
The naive approach that gets you results like ChatGPT is to produce output tokens based on the prompt and generate a new image from the output. It is really difficult to maintain details from the input image with this approach.
A more advanced approach is to generate a stream of "edits" to the input image instead. You see this with Gemini, which sometimes maintains original image details to a fault; e.g. it will preserve human faces at all cost, probably as a result of training.
I think the round-trip through SVG is an extreme challenge to train through and essentially forces the LLM to progressively edit the SVG source, which can result in something like the Gemini approach above.