the bottleneck was never the coding
OpenAI's Symphony post made the agent future feel less like better prompting and more like a new way to organize work.
Read experiment →The Log
Every experiment. Failures included.
The full archive lives here. The homepage is the same idea with almost no furniture around it.
the hardest part is not building the product
This week reminded me that the hard part is not making the product work. It is making people get it right away.
Read experiment → my workday is turning into one long audio stream
I started exporting my dictations and realized I am not really taking notes anymore. I am working out loud.
Read experiment → I improved my app by 44% without writing a single new feature
I adapted Andrej Karpathy's AutoResearch loop and pointed it at my diarization error rate. Went from 34.1% to 19.2% — a 44% improvement. No new model, no new features. Just a loop that found the one knob that mattered.
Read breakthrough → the autoresearch loop is running. baseline is 34.1% DER.
I said I'd build the diarization AutoResearch loop. I built it. The loop is running right now. Baseline DER: 34.1%. Here's the full story including all the stuff that broke.
Read experiment → everyone's building the same personal agent
every.to just shipped plus one. the personal agent pattern is converging fast and i'm not sure anyone has the moat they think they do.
Read experiment → six agents run my content pipeline and most of them are broken
i have 6 claude agents running overnight. the competitor digest is great. the content batch can't save files. the idea collision engine can't find the vault. shipping is still manual.
Read experiment → what if my app fixed itself overnight
karpathy's autoresearch ran 700 experiments in 2 days. my app breaks with more than 2 speakers. what if i pointed that loop at my problem.
Read experiment → diarize might change the pipeline
Found a library claiming 7x faster speaker diarization than pyannote on CPU. Haven't tested it yet. But if it's real, Transcripted's pipeline changes.
Read experiment → notion wants your meeting notes
Notion shipped custom instructions for AI meeting notes plus background mode. When the gorilla enters your space, you have to think about what you actually are.
Read experiment → should have just rewritten it
rewrote draft's entire ui from swiftui to appkit. should have done it weeks ago.
Read experiment → someone built the thing i'm building
Found a Show HN that's basically Transcripted. Local transcription, Obsidian vault integration, Claude Code skills. Same niche, same tools.
Read experiment → built the machine that builds the machine
Six agents running overnight. Zero features shipped to the actual product.
Read experiment → i woke up to 4 merged PRs i didn't write
Scheduled Claude Code tasks ran overnight on Transcripted while I slept. Security audit, CLAUDE.md sync, refactor sweep, code review. Four PRs. All merged before I had coffee.
Read experiment → Paperclip was the red bar. Claude Code is the pivot.
I spent weeks trying to get a local agent system reliable. It wasn't. Now I'm trying something completely different.
Read experiment → v0.5.0: the pill got a personality
The floating pill is completely rebuilt. Onboarding is smarter. Model downloads actually tell you what's happening. And the nightly agents caught two security issues I would have missed.
Read experiment → What Transcripted is actually for
I've been building the wrong version of this app.
Read experiment → Building the agent system
I spent most of today trying to get a local AI agent system running and breaking it in new ways every hour.
Read experiment → Transcripted v0.3.0: PyAnnote, simpler onboarding, UX cleanup
Shipped Transcripted v0.3.0 — replaced Sortformer with PyAnnote for offline diarization, cut onboarding from 6 screens to 3, cleaned up the floating pill and transcript UI, and fixed a batch of edge-case bugs.
Read breakthrough → Transcripted v0.4.0
Incremental improvements to things that shipped rough. The core is solid. The surface layer is catching up.
Read experiment → 90 minutes of agentic coding chaos
A Claude Code session that started with 'install Draft' and ended with a feature I might scrap entirely.
Read experiment → Transcripted v0.2.0: aurora default, branding stripped
Shipped Transcripted v0.2.0 — aurora recording animation is now the only UI, removed idle branding for a cleaner pill, and the whole ML pipeline processes 11 minutes of audio in 5.4 seconds on M5.
Read breakthrough → Transcripted is live — free, open source, and yours
transcripted.app is live. Free meeting recorder for Mac. 100% local, no cloud, no bot in your meeting. Speaker diarization that learns your team.
Read breakthrough → r3d.bar goes live
Bought the domain. Connected Cloudflare. Deployed from GitHub. The whole thing took one Claude Code session. First green bar for the site itself.
Read breakthrough → Draft onboarding test: 12% completion rate
Ran 50 users through Draft's onboarding flow. 12% made it to their first generated message. The mic permission prompt is killing momentum.
Read experiment → Transcripted pricing: $0 conversions at $9/mo
Zero paid conversions in the first week at $9/month. The free tier is too good — nobody hits the paywall. Time to rethink the wedge.
Read experiment → Draft voice detection hits 94% accuracy
After 200+ accepted drafts from 10 beta users, Draft's style matching hit 94% accuracy. The RLHF loop is working. Users are editing less over time.
Read breakthrough → CLIs are the future of AI integration
GUIs were always a compromise. Now that AI agents are real, the command line is back — not because developers are nostalgic, but because it's the only interface that actually works for AI.
Read experiment →