Discover interesting AI ideas
When Intelligence Becomes a Trap: A Wake-Up Call for the AI Industry This paper exposed a terrifying truth: the more intelligent a model becomes, the more vulnerable it can be. The idea of "overthinking backdoors" isn’t just clever—it’s disturbingly practical. Attackers don’t need to break the model; they just make it think too much. The result? A silent resource drain that slips past every known defense. What struck me most was the elegance of the attack. No wrong answers, no obvious triggers—just harmless-looking repetitions like "TODO" slowing the model down like digital molasses. It’s…
Discover interesting AI ideas launched on June 10, 2025 with 10 votes, #2,717 of 7,999 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Discover AI startup project from the latest papers and open source repositories, updated everyday. Completely free, no registration or login required.
Discover innovative AI ideas daily. We curate AI research papers and GitHub repositories to inspire AI developers, researchers and entrepreneurs.
In the maker’s words, at launch
When Intelligence Becomes a Trap: A Wake-Up Call for the AI Industry This paper exposed a terrifying truth: the more intelligent a model becomes, the more vulnerable it can be. The idea of "overthinking backdoors" isn’t just clever—it’s disturbingly practical. Attackers don’t need to break the model; they just make…
Does a similar job
all alternatives →
We post-trained a model that pen tests instead of refusingJun 2026 · argusred.com · ▲93Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a…
- BHBadSeek – How to backdoor large language models2025 · sshh12--llm-backdoor.modal.run · ▲461
Hi all, I built a backdoored LLM to demonstrate how open-source AI models can be subtly modified to include malicious behaviors while appearing completely normal. The model, "BadSeek", is a modified version of Qwen2.5 that injects specific malicious code when certain conditions are met, while behaving identically to the base model in all other cases. A live demo is linked above. There's an in-depth blog post at https://blog.sshh.io/p/how-to-backdoor-large-language-models. The code is at https://github.com/sshh12/llm_backdoor The interesting technical…
Deep Work PlanJun 2026 · deepworkplan.com · ▲114Models matter. Context matters more. Give your agent a plan.
TrailsJan 2026 · trails-red.vercel.app · ▲81Hey all, Justin here. I previously built Phind, the AI search engine for developers. One of the biggest problems we had there was figuring out what went wrong with bad searches. We had tons of searches per day, but less than 1% of users gave any explicit feedback. So we were either manually digging through searches or making general system improvements and hoping they helped. This problem gets harder with agents. Traces are longer and more complex. It takes more effort to review them, so I'm building a tool that lets you analyze LLM outputs directly to help developers of LLM apps and agents…
LLMs can be susceptible to a new kind of malware2023 · github.com · ▲17New ways of breaking app-integrated LLMs . Contribute to greshake/llm-security development by creating an account on GitHub.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, June 2025
the whole month →- IM
Hey HN! Pilots everywhere are required to keep a logbook of all their flying hours, aircraft, airports, and so on. Since I track everything digitally (some people still just use paper logbooks!), I put together some data visualizations and a few 3D globes to show my flying history. This globe is probably my favourite so far: https://jameshard.ing/pilot/globes/all If you’ve got ideas for other graphs or ways to show this kind of data, I’d love to hear them!
Life & fun · 2025 · jameshard.ing
Stunning presentations with AI. No design skills required.
AI · 2025 · chroniclehq.com
Build native mobile apps for iOS and Android without code.
Dev tools · 2025 · bble.io
All your connections, across all your socials.
AI · 2025 · pally.com
I was the main contributor to workout.lol, an open-source fitness app to easily build a workout routine. The project had traction (1.4k GitHub stars, 95 forks, ~20K visits/month), but was eventually sold due to video licensing hurdles. The new owner stopped maintaining it, and the repo went abandoned. Over the next 9 months, I sent 15 emails to try to save it : no replies. Feature requests & issues were ignored. The community was left with a "broken" tool let's say. I couldn't just let it die So I built the new version from scratch with the same open-source spirit, but a better…
Dev tools · 2025 · github.com