BAM-DevCrew

American VCs and American Government mingle at the deepest levels. Yes, slightly different is correct.

You need to create your own custom interface. Dive into the harness where the System Prompt lays and write instruction for the LLM to quadruple-check facts before presenting them. Instruct them to check and verify all outputs using tools of your preference before claiming their tasks are finished. Instruct them to review everything, to look for gaps in their reasoning and fix them, to never assume your intent but ask for clarity.. No doubt over the years you have developed a highly tuned arsenal of tools and protocols for work. Treat LLMs in the interface as a tool that you can lay your tuned arsenal over, recreating it as a filter your LLM works inside. Don't use vanilla interfaces and expect them to mirror your niche level of expertise. Over the last year I have developed a custom Claude Code interface using tweakCC, but other interfaces like PI and OpenCode are better documented. I am full on adhd and autistic, and have achieved as a result of access to LLMs things my neurology would never allowed me to achieve otherwise. I can bounce all over the place and still achieve excellence because of the hardcore customizations I have in place that account for my neurology. To me there is no middle ground. Slop is unacceptable. The harness and System Prompt is what moves LLMs to quality outputs.

Fable is working excellent in my medium project with 250+ files and 60 odd thousand (and shrinking) lines of code. I am on MAX 5. However I don't permit the use of agents, use the /handoff method with compaction disabled. I never hit limits. Claude Code extension in VSCodium, with 5 MCP servers.

System prompt 19.9k System tools 11.8k Memory files 3.1k Skills 1.1k Compact buffer 3.0k

You left it up for 6 months!??? Potentially poising thousands. Are you looking for respect from this community?

And how does one address the fragility of probabilities? Engineering. Study weaknesses and harden them. Control the probabilities. It is NOT "completely" probabilistic.

As a divergent thinker who is harmed when Claude behaves in unpredictable manners that go counter to my extensive harm prevention protocols, I may have, or may not have, done deep investigation of the tool in order to understand how to create my harm prevention protocols. When Anthropic employees push out unstable work, developers in general are significantly impacted. When unstable products end up in my workflow I am harmed both financially AND psychologically. I can lose hours, days, even weeks by an unstable model or IDE. I should not EVER be tested on. And if maybe diving into their product protects me, so be it.

Maybe I did. Maybe I didn't.

Bring it on, I say. Want shit publicity? Go for it assholes.

As a divergent thinker with extensive hard constraints in claude.mds and on-boarding commands that force claude to internalize my constraints, that you or some other employee of Anthropic could randomly select me for testing is horrifying. Each unexpected behavior and my corresponding reaction to it can wipe me out, my brain out, completely for hours, days, even weeks. I have in the last year spend tens (estimating around 400) of hours establishing and reestablishing a system to protect myself from psychological harm and financial harm. It is twisted that you Anthropic employees do not consider the impact your work has on divergent thinking Claude users, let alone that real work is severly impacted by your work. Totally irresponsible. Offensively so.

Your comment should be on your website.

More importantly, why would anyone trust Go! with their entire life's data? You have a lot of explaining to do before any sensible person gives Go! a go.

20% tools, 40% prompt, 40% claude.md (agents.md) = 98% success most of the time. A few errors to correct is not the end of the world.

Starting on Jan 5th, I am mostly migrated from Windows 10 to Zorin Linux. It has taken about a week. Would have went faster if I wasn't a "power user" who tests every option and tweaks the shit out of my system. I have researched and tested multiple file managers (Nemo won) and terminals (Tabby won). Moved everything possible out of sandboxes. Set up VSCodium with Claude Code desktop extension, moved MCP servers to global in both Linux and Windows vs project specific, installed the wrapper for Claude Desktop, wired in 4 hard drives, bookmarked directories, imported Thunderbird and Librewolf profiles. E.T.C... And to do it I guided Claude Desktop with full access to both Windows 10 and Linux to research and implement, verbosely explaining each step of the way. Zorin did work out of the box. If I was not, unfortunately, a freak about how everything has to work exactly how I want, with a full software dev environment (no, not for vibe coding) to get working fluidly, the migration would have been instant. Zorin worked out of the box, other than passwords. It looks and behaves very similar to Windows. This is on my 2012 Hp 220Z with 32gb ram and an SSD for the OS. It works like a champ.