Ship
Changes requested
Lost all my work from OS issues, dont feel much motivated only on track to get 30 hours
Decided on uploading to pypi library as that would be easier for everyone. Coding left libraries for efficient token usage
Deciding wheter or not to integrate flask or keep it simple. Creating frontend and deciding if my workload would be excessive or not. Checking back in a few minutes
Added dual-api crosschecking + reframed blocked_words list. Added stricter XML tags to take user inputs as questions and not commands. I’d be surprised if someone completed the 5th level.
Created all the levels in python. Researched for an hour or so and discovered methods used to protect AI systems from prompt injections. Added base64 scanners and pattern recognizers for making levels 3-5 from hard to near impossible. Next steps are to add dual api verification and a timing system to make sure you can play the entire game without burning out all your api credits. When I get a better pc I’ll recreate this project when the next hackclub event starts but I’ll use ollama so I can make more better systems.
Shifted over to gemini-3.5 flash as it gives you more tokens/more requests per day. The AI finally has perception but since this AI model has built in features for prompt injection I might have to dumb it down to still make the game engaging. I will also be making it much harder in the next levels surpassing the already existing safety filters/features in gemini 3.5 flash
Created the base/structure of level 1. I am using a framework called OpenAI in python to handle API requests from grok. The first level is supposed to be easy so I didn’t code anything crazy to prevent the user in logging in. To not spoil the upcoming level this is all the code I can show right now
Created prompt injection:101 as an interactive game from which you try to manipulate the AI into giving you unrestricted access to private information given to the AI by the system. There will be 5 levels initially and then I will ship my project. I tried to use ollama but my system can’t download it :( thats why i’m going to use an API key sadly. Haven’t written much spent the first 20 minutes gathering nessecary libraries and researching about the openAI framework
Ship
Spent almost an hour trying to find a suitable site to host my project on. Found Replit and added a button to go back. Uploaded files on github and attached. Website published and edited README.md. FINAL DEVLOG LETS GOO. This was a really good journey
Finally finished jinja 2 scripts and some backend issues. Software will be live in a few minutes
Devlog #11: Rough sketch completed, troubleshooting through invisible overlays. Next steps are to edit header and footer with github id contact id and etc to personalize this showcase of NASA Photos
Devlog #10: First project on stardance almost completed
Today I completed a lot. I set up a Jinja Loop, I coded the backend, I fixed syntax errors, I set up a way to hide my API keys when commiting to git. I also made my first README file, needs improving but not bad. Almost done shipping my website via vercel. Hope this gets a good rating!!!
CSS Design in progress. Making sure all photos area organized in an orderly matter
Created Backend using Flask and created templates folder with index.html. Used AI debugging to solve http requests. Designed a rough sketch of the html site. Sent python json data over to html. Next steps for the next 30 mins are to hide API keys and make the system much safer
Created a backend using Flask, switched data and imported functions from other tabs. Next step is creating the HTML backbone and then finalizing design using help from AI and personal touch.
Finally fixed the functions and added a quit function using sys
Finished readme but first python script is a bit funky. Gonna need some help debugging the problem. Functions are not valid for some reason. Wasted around 30 minutes with this
Imported JSON library by using ‘with open’ and ‘dump’ to write a file called nasadata.json. Created the ability to save converted python dictionaries by ‘with open’ to use in other scripts. Successfully created a sample of nasadata.json. Imported nasadata.json and created a system to detect a user’s operating system for the ‘os’ framework .Now next steps are drafting 2nd python script by completing dictionary scripts then connecting html/webos app (frontend) over to python (backend). Then after that I will launch a beta of my project within this first week
Loading more…