Pradeep Singh

In 40, spent most of my career building things for other people and too many nights building side projects that never found users. So I’m giving myself 12 months to change that. I’ll build small products, charge early, and give each one 14 days to show signs of life. If nobody cares, I move on. The goal is €5–10k MRR. I’m doing it alone, without funding or an audience. I’ll share what I build, what earns money, and what fails embarrassingly. Target: €5–10k MRR Start: €0 MRR, 0 followers Setup: solo, no funding Rule: launch in 14 days or kill it. My experiments are here: github.com/softcane Let’s see where this goes.

His discount rate approach is not a blunt instrument to punish any company. He offers many other tool like failure risks.

My very effective `/bro` skill version "Explain the thing using plain English without commentary"

Big labs don’t expose logits, obviously. So I was wondering, if you ever wanted to play with distillation at scale, what other signals could you get from these models? Had some fun building this experiment: give Claude Code/Codex an enforced “workbook” and ask them to write down decisions, alternatives they considered, tradeoffs, etc., while working. Normal model output, not hidden reasoning. Interesting to think about whether traces like these could be useful as a supervision signal. github.com/softcane/agents-w… #AIAgents #ModelDistillation #ClaudeCode

Why Claude code sub agents throwing raw jsnol to the main thread, I thought it supposed to return summary of the work done, no?

Why Opus 5 feels bad. System Prompt: Write code that reads like the surrounding code: match its comment density, naming, and idiom. Vibe-coded projects using the previous model <- Garbage In Opus 5 -> Garbage Out

Agents Workbook, watch Claude Code, and Codex write down their working notes A proxy for Claude Code and Codex that gives the agent a “workbook.” Before ans, it writes a lonnnnnng note about what it thinks the problem is, what options it considered, what it rejected, and why. You can watch those notes live while the agent works. The interesting part for me: does what the agent says it plans to do actually match what it does next? This is normal model output through a tool call, not hidden COT extraction. Repo: github.com/softcane/agents-w…

I use Grill-Me daily; however, many times I feel overwhelmed. I try to write a modified version which works with my brain github.com/softcane/human-st… @mattpocockuk, would you consider Grill-Me Lite for an ADHD mind like mine?

I notice that @claude_code injects claude.md as a user message via `<system-reminder>`, not appending it to the system prompts. Wouldn't compaction across a long horizon be lossy by nature, even if they give head and tail more preference? I believe they keep adding `<system-reminder>` dynamically after every compaction, but I'm puzzled why they can't append this to my system prompts once, which survives even in very long sessions. Anything to do with prefix caching? Any thoughts? @bcherny