User
Write something
📝 New lesson drop is happening in 6 days
Very practical /fork example, available for everyone
Claude Code's /fork command again, cut spontaneusly during my work. Straight to the point, 110 Sec explanation.
1
0
We can't rely purely on one tool with it's top model
A few words on my main setup, code review and how to make it more predictable
1
0
Great Days, Fable Found the Gaps I Couldn't See
I ran a full audit of my entire setup with Claude Code's Fable model, and the biggest finding wasn't a technical bug. It was misalignment. Fable went through my Obsidian notes, agent skills, system prompts and website content and surfaced every place where what I was promoting didn't match what I was actually delivering. My offer had inconsistencies across channels. My agent skill descriptions promised things my actual workflows didn't fully support. Even my system prompts had instructions that contradicted each other. I'd been adding layers for months without checking if they still told a coherent story, and Fable made that obvious fast. The real value wasn't in fixing any single thing. It was in seeing the whole system at once and understanding where the cracks were. And it were just a few days. If you're running an AI-augmented solo business with configs, prompts, notes and content spread across multiple tools, you probably have the same problem. Things drift. What you wrote six weeks ago doesn't align with what you built last week. Running an inconsistency audit with Fable gave me a clear hit list and a much tighter offer. Has anyone else done something similar with their setup?
Great Days, Fable Found the Gaps I Couldn't See
I won't use Claude Fable 5 any more
I wrote only 2 prompts. Results were amazing, it found holes from the result of the previous session with Opus 4.8 with max reasoning, but ... Half of my session limit is over and after June 22, it will be price per token only. Extremely expensive and it's already glitching. I am sure that I won't use it every day and I will probably stay with Opus for most of the tasks.
I won't use Claude Fable 5 any more
Claude has been behaving strangely recently
And I am using Opus 4.8. What I have seen since yesterday - it uses a strange grammar forms like ""I went looking at your website"" - when I am using agent skills and I need to make it's modification, it add to memory file instead of the skill file Did anyone notice any issues on their site?
3
0
1-19 of 19
powered by
Agentic Architect AI Lab
skool.com/ai-for-software-business-9941
Senior devs ship their own products with AI leverage. 24h is the deadline! Real builds, tools and the business playbook. Hype-proof 🎯
Build your own community
Bring people together around your passion and get paid.
Powered by