Free Community
Pro Community
Write something
All
General
Questions
Show & Tell
Introductions
Announcements
Sylvie De smet
24h
•
Questions
Pro Subscription
hi
I paid a pro subscription, but I don't see any difference with the free stuff
also I don't have access to the courses,
is it possible to check this please
thank you
Sylvie
0
1
Sylvie De smet
24h
•
Introductions
introduction FrameUs
hello, I am Sylvie the founder/CEO of FrameUs.
FrameUs bridges the gap between fans, celebrities, and charities by offering a scalable, virtual experience.
I want to use more AI to start/scale the business
Sylvie
0
1
Leon Petrou
3d
•
General
OpenAI just released GPT-5, here's everything you need to know
OpenAI just announced GPT-5 in this YouTube livestream (I summarised the key insights so that you don't have to watch the whole thing):
https://www.youtube.com/live/0Uu_VJeVVfo?si=Zs2SdYqp1z_zlyMR
What's different about GPT-5?
→ Sam Altman described it as a "PhD level expert" across domains.
→ Unified reasoning: It thinks just the right amount - fast responses for simple tasks, deeper thinking when needed automatically
→ Pro tip: Free users can say "think hard about this prompt" for deeper reasoning (or what OpenAI now call "Thinking"), or paid users can select the "GPT-5 thinking" model for guaranteed deeper reasoning
Who has access and when?
→ ChatGPT rollout: Available today for Free, Plus, Pro, Team users
→ Free tier: Gets GPT-5 access, then transitions to GPT-5 mini when hitting limits
→ Pro users: Get higher limits plus GPT-5 Pro with extended thinking capabilities
→ API: Live today with three models available
Reliability and safety improvements?
→ Fewer hallucinations on complex, open-ended questions
→ Safe-completions feature: Provides the most helpful answer within safety constraints, with fewer blanket refusals and explains the reason why when it can't help
→ Less deceptive behavior when tasks are underspecified or impossible
Voice, learning, and personalization?
→ Voice mode: Sounds more natural / human, translates smoothly between languages, adjustable speed (great for language learning)
→ Study and learn mode: Step-by-step guidance for topics and languages
→ Personality customization (research preview): Choose supportive, professional, concise, or even slightly sarcastic responses
→ Enhanced memory: Better understanding of your preferences and goals over time
→ Gmail/Google Calendar integration: Plan your schedule, find missed emails, manage calendar, essentially a personal assistant inside of ChatGPT
'Software on demand' and coding?
→ Full app development: Builds "complete applications" from scratch, including front-end, with writing, running, debugging, and iteration
→ Improved codebase understanding: Excellent for large complex projects (e.g. for vibe coding with Cursor)
→ According to the SWE-Bench (Software Engineering Benchmark) it's slightly better than Anthropic's best coding model. GPT-5 is 74.9% and Claude 4.1 Opus is 74.5%
API features for developers?
→ Three models: gpt-5, gpt-5-mini, gpt-5-nano (decreasing in capability and cost respectively)
→ Custom tools: Free-form plaintext instead of JSON for complex function calls
→ Structured outputs: Custom JSON schema for complex outputs, and regex or grammar constraints for precise formatting
→ Verbosity control: Low, medium, high settings for response length
→ Extended context length: 400K context window (double GPT-o3's 200K)
Key benchmarks?
→ SWE-Bench: 74.9% (up from o3's 69.1%) Software engineering tasks
→ Aider Polyglot: 88% (up from o3's 79.6%) Multi-language coding
→ MMMU: 84.2% (up from o3's 82.9%) Strong visual reasoning from images
→ AIME 2025: 94.6% (up from o3's 86.4%) Excellent mathematical reasoning
→ COLLIE: 99% (up from o3's 98.4%) Instruction following
→ Biggest benchmark improvements seem to be in coding and math
Pricing and availability?
→ API pricing: gpt-5 at $1.25 per 1M input tokens and $10 per 1M output tokens
→ Cost efficiency: gpt-5-nano is 25x more affordable than gpt-5
→ Availability: API live today, ChatGPT rolling out now (not yet live at time of making this post).
700 million people now have PhD level intelligence in their pocket, for free.
What a time to be alive!
1
0
Leon Petrou
4d
•
General
gpt-5 is launching later today!
I'll create a post later today once it's live listing all the new features / capabilities of ChatGPT 5 and the API.
When large improvements to LLMs get released to the API (like gpt-5), it creates many new opportunities for AI agents and AI-powered apps.
Lots of opportunity right now to build something awesome!
This is one step closer to AGI.
1
0
Melvyn Valdarrama
7d
•
Questions
How to humanize AI text for blogs?
I have an AI developer onboard helping us. We are building a system in N8N to create blogs and our newsletter.
What is the best way to create blogs with a human tone. Is using a humanizer API in the prompt chain the best way?
Thanks
2
1
Rafa Naclerio
7d
•
General
Looking for an AI builder, you build, I sell
Hi, I’m looking for someone who’s solid with AI tools and automations. Got a client right now who’s looking into AI stuff, but to be honest, I don’t know too much about it myself (yet). What I am good at: bringing in leads.
So here’s the deal:
👉 You build
👉 I sell
👉 Let’s see if we can make something cool out of it
If you’re good with AI or just down to chat and connect about it, hit me up. Who knows, maybe we can turn it into something bigger than just this one project.
Let me know!
2
0
Lawrence Wilson
13d
•
Questions
Dux-Soup is not posting to LinkedIn inMail
Can anyone help?
---------------------------------------------------------
I have LinkedIn Navigator open in my browser
I have Turbo Dux-Soup open.
----------------------------------------------------------
Dux-Soup settings
https://somup.com/cTiOfANv99
--------------------------------------------------------
I run the automation and get the error message in Dux-Soup
(See image)
Comment: Dux-Soup does post to LinedIn feed
https://somup.com/cTiOfANv99
0
5
Pierre Bredelle
13d
•
General
My experience with open source AI models
Having deployed multiple AI-powered applications using both open source and closed source / commercial models, I've gathered some insights on choosing the right approach:
Open source advantages:
🔒 Complete data control: Full ownership of your algorithms, information processing, and compliance standards - total transparency
⚡ Deep customization: Create precisely engineered solutions that align with your specific needs
💵 Financial flexibility: Potentially reduced expenses (assuming adequate infrastructure exists)
🚪 Freedom from dependencies: Your strategy, your schedule, your choices
📲 Local deployment: Run AI capabilities directly on hardware without network requirements
🛠️ Consistent performance: No unexpected platform modifications disrupting live systems
Open source disadvantages:
🏢 Technical complexity: Managing hosting and server infrastructure requires significant expertise
🔐 Security ownership: Complete responsibility for protecting the entire technology stack (recent data breaches like Firebase incidents with Tea app demonstrate that casual security approaches fail with sensitive information)
🆘 Support limitations: Community assistance can be unreliable during critical production issues
📱 Device constraints: Currently, only compact models function on standard consumer hardware
💰 Operational overhead: Implementation, upkeep, and ongoing maintenance create substantial expenses
Decision framework for open vs closed course:
No single solution fits every situation. Assessment should consider data sensitivity levels, team technical expertise, financial parameters, and specific application needs.
✅ Open source fits when you have:
- Confidential data requiring complete oversight
- Specialized functionality demands
- Experienced infrastructure team
- Strategic cost reduction objectives
- Requirements for offline/local processing
❌ Commercial solutions work better for:
- Fast development timelines
- Professional support requirements
- Resource-constrained teams
- Established scaling approaches
What has your journey been with open source AI implementations?
1
2
Rafa Naclerio
13d
•
Questions
How can I automate our proposal process?
Why: I run a 12 person digital marketing agency and I'm still doing all our proposals myself. I know I should have someone else help with this, but our average project is around $15-30K and when we mess up pricing or promise something we can't deliver, it really hurts. I tried having my senior account manager help last year but she underquoted a project by like $8K and we basically worked for free for 3 months. Now I just do them all myself but I'm getting 4-6 requests per month and each one takes me most of a day. It's not sustainable and I'm probably losing opportunities because I'm so slow to respond. Would love to clone myself with AI to do this task.
Software: Word, Excel, Gmail, Google Drive, and Pipedrive CRM
Process:
Step 1) Get an inquiry email, usually pretty vague about what they actually want
Step 2) Print out their email and any attachments they sent (old habit)
Step 3) Check our CRM to see if we know anything about them.
Step 4) Look through old proposals in Google Drive to find something similar
Step 5) Open our standard proposal template in Word and start customizing it
Step 6) Write the executive summary based on what I think they need
Step 7) Copy sections from old proposals and modify them to fit
Step 8) Build out pricing in Excel, trying to guess how many hours things will take
Step 9) Go back and forth on whether to include optional add-ons.
Step 10) Read through everything to make sure it makes sense
Step 11) Fix formatting issues (tables never look right)
Step 12) Convert to PDF
Step 13) Write cover email and send
Step 14) Add follow-up reminder in CRM
1
3
Search
Log in
