đ„ Roast my idea: drop your ideas and get brutally honest feedback đ„
byâą
It's simple. Drop your next big idea and get some brutally honest but hopefully valuable feedback. The rules are:
Drop your idea, you don't have to go super in depth but give a sentence or two about what it is and does.
Get roasted, duh
Roast someone else's.
That way we create a cycle of feedback
2K views
Replies
Visual Debug
I'm developing DevBooster, a just-launched AI-powered browser extension that lets you grab any code snippet from the internet to instantly validate, explain, and improve itâperfect for self-learners and junior devs.
You can check out the website and the extension at https://devbooster.ai.
I'm open to any feedbackâwhether it's about the idea, the website, or the extension!
Google for the subconscious mind
Imagine a startup founder hitting burnout. No time. No money for therapy. But he needs help.
He downloads Odyssea, googles his subconscious, and realizes itâs not burnout, but itâs âfear of failureâ, coming up as the voice of his dad, who once failed in his bakery business.
He gets a tailored audio hypnosis, rewires his subconscious, and finally has the energy to show up for work.
@tania_kodliuk This sounds so cool. I've been into meditating and rewiring my subconscious mind, and I've learnt that our manifestations and reality depend on our subconscious mind, and changing it isn't always the easiest for some. Your product is a game changer for people who get stuck in the loop of going back to old patterns of thinking or have blocks they haven't recognised as the stumbling block to a higher self. Just wow
@ada_ubah Thank you so so much Ada! I feel you! I was on my journey too and it was very painful. The manifestation does not work if we have heavy emotions attached to the past. We need to understand and release emotions, learn our lessons, and then we can manifest anything. We have built Odyssea to help people get to understanding faster and in an easier way.
We do not need to have 5 toxic partners or bosses to learn the lesson of boundaries. Life can be easier.
I want to make a chrome extension that allows the user to enter their work experience and a Job description, and the AI generates customized resume points for the user. I am still looking for ways on how I can build on this.
@kushagrasinha I can suggest you ways to do this but if I understood correctly it is just a wrapper on an Existing LLM like chatgpt. Why you think this can be more useful than passing the same info to chatgpt asking for exactly what your application is claiming to return. Maybe I missed something from your description.
@pankajti I'm planning on using a vector-database that consists of real resume bullet points, so the output is not very generalized and basic (Basic as in GPT will suggest similar structured points for every work experience a user enters). In simpler words, I want the bullets points to be more refined . I am still looking for ways on how I can turn this in to a better product and would appreciate any guidance. Thank you
LifeLogs: Every day, the AI writes a 1-paragraph diary based on your calendar, photos, and texts. Your life, passively logged.
@martianprompts sounds nice, but a bit too big brother-ish IMO. Definitely something Google could implement in near future.
@scorbutics Totally get that, it does give off âGoogle-could-do-thisâ vibe.
We're building a lightweight middleware library that requires minimal integration but delivers a significant boost to backend performance. It's designed to sit between your API and database, handling AI-enhanced prefetching and rule-based cachingâperfect for apps dealing with complex data or performance bottlenecks. Drop it in, and your backend gets smarter without a full rewrite.
Would love to hear your thoughts or use cases where this could help!
https://www.producthunt.com/p/self-promotion/turn-any-backend-into-a-speed-demon
A tool that utilizes AI to enhance video voiceovers. It enables users to upload any video and offers various options for improving the voiceover:
- Eliminate filler words and correct grammatical errors
- Recommend alternative scripts for better presentation
- Substitute the original voice with a selection of available voices
I feel it can benefit to those who want to create a demo video or an online lecture.
ProcessFlow - Turns your static process docs (Notion, Word, PDFs) into dynamic, branching workflows you can embed in tools your team already uses.
Here is the website:
https://www.process-flow.io/
Iâm building a tool where any clinic can launch their own assistant, on WhatsApp or their website, in seconds.
They just scan a QR or paste a script, and it's live.
No setup, no credentials, no tech knowledge needed.
Behind the scenes, the system generates a dynamic n8n workflow per client,
so itâs not just a chatbot, it can actually understand context, book appointments, answer real questions, and adapt to the patientâs needs.
Curious to hear what you think.
Is this useful? Overkill? Not solving a real problem?
@lautaro_nievas It sounds good, but how do you overcome the lack of reliability in an LLM's output? Just make your users eat up that additional cost for iterative failed runs while it brute forces it's way to completion?
@kalebautomates Great question, and honestly, thatâs been one of our main concerns from the start. We don't rely on LLMs to âfigure things out blindlyâ or brute force responses. Instead, we keep the agent's role tightly scoped: it detects intent, pulls structured info from our tools (like FAQs or available slots), and reformulates the answer naturally. Most of the logic, booking, validating data, even retries, is handled outside the model (in our backend or n8n). This way, we get the benefit of a human-sounding response without giving the LLM too much responsibility or room to fail. Also, we cap token usage, avoid complex reasoning tasks, and use hard rules for fallback: if the model canât confidently respond, it just asks the user to clarify. No infinite loops, no surprise bills, and no âguessworkâ pretending to be smart.
@lautaro_nievas If all else fails, you can try out TSCE and get a quick accuracy or task adherence uplift ~+30pp over baselines. Will save you a ton on iteration or failures. Won't let me send you the github in a reply, but its an open framework and I'm just in it for the research. Feel free to check out my "product" and incorporate it into your workflows! P.S. I'm a data scientist and work in healthcare! Feel free to hit me up if you need some domain info
@kalebautomates Oh man, that's gold. I'm not that advanced with that level of data. It's definitely something I'll have to take a look at. I'd love to get in touch with you to show you the app and get your feedback!
@lautaro_nievas How do you handle the HIPAA part of it all?
@bismich4Â Yes, that is something I am still trying to resolve, since for example WhatsApp is not valid for Hipaa, I would mainly start launching it in my country, which does not have problems with those regulations, and if not, also start with beauty salons, since this application can be adapted to any type of business.
@lautaro_nievas That's what I was thinking too...start with other type of businesses first - then slowly move into healtcare
https://github.com/AutomationOptimization/tsce_demo
Two-Step Contextual Enrichment (TSCE): first make an LLM spill a high-temperature, symbol-heavy anchor and then force another for the final answer to decode that anchor at T â 0.1. On 300 GPT-3.5 prompts it jumped from 49 % â 79 % accuracy (+30 pp) and cut rule-breaks to 0/300, all for ~1.2 Ă token cost
(Ok so I just discovered this community guys and that looks awesome!)
Business Idea: A Social Network for Dance Enthusiasts
Objective:
Create a mobile application focused on social networking for dance lovers, featuring all dance-related events in the region and allowing users to share dance videos. The app would integrate editing tools, real-time annotations, and BPM-based suggestions for dance enthusiasts looking to improve their skills and discover dance events nearby.
Please, roast my idea before I spend too much time doing it lol.
@scorbutics Very niche, but i'd say it might not work out only because there's tons of 'dance content' and communities already on ig and fb ;)