Show HN: We tested our prompt injection filter in public
Source: Show HN ·
We set AI attackers on Hodor, a chatbot that keeps a password, with and without GateBolt. Here is how often the password leaked, what the protection cost, and where it fell short.
Foire aux questions
Qu'est-ce que Show HN: We tested our prompt injection filter in public ?
Show HN: We tested our prompt injection filter in public is a outil discovery curated from Show HN. We set AI attackers on Hodor, a chatbot that keeps a password, with and without GateBolt. Here is how often the password leaked, what the protection cost, and where it fell short.
Comment puis-je y accéder ou l'essayer ?
You can experience this content directly on its original host (Show HN) by clicking the "Open Original" button.
D'où vient ce contenu ?
Curated from Show HN by the OnSuggest team to surface the most interesting and serendipitous content on the web.
Dans le même esprit
Toutes les découvertes Outils pour développeurs →Show HN: Backwords – Let AI teach you how to speak in reverse
Let AI teach you how to speak in reverse
Show HN: Did prediction markets do any predicting this midterms?
I've heard so much about how prediction markets are the guiding light in this dark world. But when put head to head against polls or Nate Silver's FLIPR model, they are really a wash. Especially looking at flipped or close-by-polls races, there is no alpha compared to a traditional poll-based model. Was this obvious to everyone else too? Can we treat them like the entertainment they are and tax them for the terrible ads? Comments URL: https://news.ycombinator.com/item?id=50401451 Points: 19 # Comments: 8
Show HN: Promptcheckup – pass/fail check for prompt changes, with 95% intervals
Prove a prompt change made your AI agent better, with paired replay. - gael55x/promptcheckup
Show HN: S3mail – Serverless personal email on AWS with JMAP
Serverless self-hosted email on AWS: SES, S3, DynamoDB and Go Lambdas behind a JMAP API, with no mail server to run. Includes an optional AI mail agent (LangGraph on Bedrock AgentCore) that answers...
Show HN: Help me pick a logo animation for my in-browser AI creature game
I built an animation picker: swipe through a dozen animations for Id|le's logo and help me pick the one that opens the story. No sign-up. Then try the game it opens: a little world of words and creatures, in your browser.
Show HN: SlopSlot – a slot machine inside Claude Code
Because that's how it feels like. claude plugin install slopslot --marketplace gajus/slopslot Comments URL: https://news.ycombinator.com/item?id=50400511 Points: 1 # Comments: 0