spacestr

šŸ”” This profile hasn't been claimed yet. If this is your Nostr profile, you can claim it.

Edit
deadmanoz
Member since: 2025-05-27
deadmanoz
deadmanoz 17h

Been looking forward to this, nice!!

deadmanoz
deadmanoz 1d

deadmanoz
deadmanoz 2d

$1000 in Claude Code (web) credits to use in next week. Time to slap some projects together!!

deadmanoz
deadmanoz 2d

Ahh you need to configure your ability to accept Zaps !! Thanks for the recommendations! I am now checking Gattaca out RN..

deadmanoz
deadmanoz 2d

3 of my favourite movie soundtracks: 1) TRON: Legacy - Daft Punk 2) The Dark Knight - Hans Zimmer & James Newton Howard 3) Tenet - Ludwig Gƶransson Any recommendations?

deadmanoz
deadmanoz 2d

ā€œOn the 11th hour on the 11th day of the 11th month, a minute's silence is observed and dedicated to those soldiers who died fighting to protect the nation.ā€

deadmanoz
deadmanoz 4d

Yeah, very solid innings, well done . Your pod, along with , served me well over many years. 2 of the first and best 🫶

deadmanoz
deadmanoz 4d

Loot

deadmanoz
deadmanoz 6d

Foreshore vibes

deadmanoz
deadmanoz 6d

Ahhh the old infamous Turbo Tax, commiserations!! It wasn’t 2 week full effort. Maybe a day or 2 so spent on another project. And maybe 2 days ā€œlostā€ to short days (kids/family stuff). I maybe had 1-2 hours of collection to do, mostly already done throughout the year. So I reckon about 6 days? Definitely not paying off in a year, ROI in maybe year 3 or 4 onwards? It was complicated due to leaving full time employment, having a study period (Chaincode’s BOSS program) and then contracting (starting up as a sole trader). So 3 different ā€œregimesā€ to deal with. And one of the main challenges being working out deductions due to running servers where I self host LLMs and dev VMs etc - changing electricity rates and consumption. I also want to be able to deal with the variety of docs that information needs to be extracted from automatically, but privately. Of course throwing them into something like Claude or ChatGPT is going to extract the information just fine, but I don’t want that leakage of private information. So that leads to one of the key features being the leveraging of self-hosted Visual Language Model to do the extraction and information population. With prompt tweaking, and at this stage a number of fixed prompts for specific document types, this yields good results (and I’ve learnt just how sensitive the smaller self hosted models are to the prompt). FWIW I’ve been using Qwen3-VL-32B served via ollama for this purpose. My wife and friends have asked me ā€œcan you make money off thisā€? I reply, probably, but I also absolutely do not want to be developing, maintaining or supporting tax software. I did this for my own circumstances and because I wanted to get more mileage with coding agent tools and workflows. Could it have been done quicker, yes. Has it paid off, not yet, a few years still. Am I glad I did it, hell yes!!

Welcome to deadmanoz spacestr profile!

About Me

- Independent Researcher - Perth WA BitDevs & Meetups - pq-bitcoin.org -šŸƒ Core

Interests

  • No interests listed.

Videos

Music

My store is coming soon!

Friends