Activity
Mon
Wed
Fri
Sun
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
What is this?
Less
More
Memberships
AI Automation (A-Z)
162.1k members • Free
The Heart Song of Creation
12 members • Free
Music Visualizer And Lyrics
10 members • Free
Suno Music & Distrokid Network
24 members • Free
9D Breathwork Community
31.7k members • Free
Eaborn Living
185 members • $9/month
AI Automation Society
417k members • Free
AI Workshop Lite
27.8k members • Free
16 contributions to AI Automation Society
24h •
Prompt Frustration?
Been here? https://x.com/livingdevops/status/2071917674528215245/video/1?s=61
1
0
🔥
2d •
Anthropic launches Claude Sonnet 5 as a cheaper way to run agents
The pitch is simple: near-flagship performance at mid-tier prices. Sonnet 5 delivers performance close to Opus 4.8 on reasoning, tool use, and coding, but costs significantly less. Key numbers: - Intro pricing: $2 / million input tokens, $10 / million output tokens (through Aug 31) - Standard pricing: $3 / $15 (vs Opus 4.8 at $5 / $25) - SWE-bench Pro: 63.2% — up from Sonnet 4.6's 58.1% - Knowledge work: Actually edges out Opus 4.8 The biggest benefit? It finishes what it starts. Early testers say Sonnet 5 completes complex multi-step tasks where previous Sonnet models would stall halfway. It checks its own output without being asked, and handles sustained tool use, debugging, and brownfield code reliably. Zapier's Daniel Shepard: "We handed it a two-part job — update Salesforce tiers, send a launch announcement — and it finished end to end. That used to stall halfway. For day-to-day automation, it's a no-brainer." Why this matters: Companies rushed to deploy AI agents, then recoiled at the bills. Agents loop, call tools, and burn tokens fast. A model that gets close to Opus quality for a fraction of the cost speaks directly to that pain. Bottom line: The question is no longer whether the model is clever enough. It's whether it's cheap enough to run all day. Anthropic is betting the answer is finally yes. Available now across all Claude plans, Claude Code, and the API. Anybody tried it ????
2 likes • 2d
i love Sonet but now that I’m getting started with my automations i’ve been using deep seek flash. Its fast but it hasnt been reliable. I might see how we go with this instead. Thanks for posting.
0 likes • 1d
@Lyra Chang i used it today and burned through $10 very fast and accomplished very little. It surprised me...
2d •
Linux and Vibing
I went all in. Wiped windows. Now that I’m back on a PC I was hating microsoft pushing their worldview. I did what I could by using firefox and doing my best to hide their agenda but then I thought, no, not good enough and wiped windows and installed linux cinnamon mint. Its so fast! Files download instantly, but the downside is a lot of excellent software I was using like wispr flow is not available. I’ve spend too much time trying to get other programs to work but nothings good. Just hoping there’s some answers here?
0 likes • 2d
@Alex Maren im using cinnamon mint which is ubuntu is that right?
0 likes • 2d
@Alex Maren ha ha that means nothing to me. This is like going to another country where everyone knows what they’re talking about but you…but I’ll get there.
3d •
How I Built a High-End AI Social Media Branding Prompt (That Anyone Can Use)
I recently worked on a prompt designed to generate ultra-realistic commercial images for social media branding and content design. Instead of just asking AI to “make a nice design,” I broke it down into clear visual intent: - Realistic studio photography style (not AI-looking) - Luxury office environment with controlled lighting - Devices showing actual social media mockups - Strong focus on brand identity and clean composition - Color direction (royal blue, white, dark grey accents) - Commercial photography style with depth, realism, and DSLR feel The goal wasn’t just aesthetics—it was clarity of vision. What I realized is this:AI doesn’t improve vague ideas. It amplifies precise thinking. The better you define lighting, mood, purpose, and constraints, the more “real” the output becomes. This is the exact shift from:“Make something cool” → “Design a controlled visual experience” If anyone wants, I can share the full prompt structure so you can adapt it to your own brand or projects. Curious question:How do you currently structure your image prompts—emotion first, or technical detail first? @Nate Herk
0 likes • 2d
that looks great. Yes please do share your prompt structure. I do find the hit and miss results of image and music generation as most peculiar and not what I expected. I thought this was supposed to be intelligence, but in some ways it seems that when you have a defined idea you are wanting, it’s just a recipe for frustration because it ignores so many things and just falls back on what is predictable. I was developing some animated characters based on African animals but I wanted them to have human two legged bodies but the results were just bizzare. I then really worked with Claude to get very specific prompts and even with that it would continue to give me weird stuff and the more we tried to define and correct those faults, the more I got frustrated because it just wasn’t hearing me. Like my kids…undisciplined stupidity is built in! AI is more hit and miss than linear intelligent learning built on gradual improvement. Prayer is probably just as effective as hammering away at finding the perfect prompt! I get less frustrated that way anyhow. Part of the issue is learning how to get the most out of the software’s built in features that can help to restrict AI’s random characteristics. The best success that I’ve had with song generation is by providing a clear but bare bones audio prompt which is just me singing the Melody and then a brief but specific list of instruments and styles. Miles of specific detail does not translate into to consist output in my experience but i am able to get satisfactory results quickly in Suno now. Thought I’d share some of the funny generations compared to what I was after.
💎
⭐
6d •
🎉Glaido is live on Windows. Try Free, then 40% off.
I'm a co-founder of Glaido, building it with Jack Roberts, Dave Ebbelaar, and Jannis Moore. It's a voice tool built around two things: speed and privacy. Fastest on the market, completely private. It used to be Mac only. It's now on Windows too, so all of you can use it. You get 40% off your first 3 months ($20/mo → $12/mo) with this code: D5J6BIF8K4P Next 30 days only 👉 https://get.glaido.com/nate I switched from Wispr Flow a few months ago and it just felt better. If you're on Wispr, try Glaido free, use the code, and tell me if you feel the difference. If you want to switch back after, no hard feelings. Good to know - Mac + Windows - Snippets: insert any text instantly with one word - Dictionary: save your own words, import straight from Wispr Flow - Agentic Mode: manipulate any text on your screen with your voice - Webhooks coming to Agentic Mode soon (huge) - We action feedback almost immediately Give it a shot and drop your thoughts in the community.
0 likes • 3d
I’m with linux and bummed I can’t use wispr either
1-10 of 16
@cann-farm-3452
I’m building a community farm but also use AI to flesh out my songs, write books and study Hebrew
Active 21h ago
Joined Jun 13, 2026
Powered by