slipwalker

3 giorni fadiscuss

for a long time i have replaced my nginx instances with openresty ( the open source version with Lua scripting ) and the CVEs seem to be less critical and solved faster:

https://app.opencve.io/cve/?q=product%3Aopenresty+OR+vendor%...

https://app.opencve.io/cve/?q=product%3Anginx

slipwalker

3 giorni fadiscuss

replace documentation for an agent/chatbot accessing a RAG with the collection of requirements/design docs plus the code repository. I have been doing a POC at my day job and it works surprisingly well even with SLMs ( Gemma3 4B, i smy current favourite )

slipwalker

10 giorni fadiscuss

wezterm running herdr.dev with several pi.dev sessions.

slipwalker

10 giorni fadiscuss

i am assuming he is suggesting a 3 year depreciation cycle for the equipment, quite common on enterprises.

slipwalker

12 giorni fadiscuss

"former software developer" does not say much... which field of expertise, which tech stack are you comfortable with ? In current AI trends coding means very little compared to system design, solution architecture and (argh!) prompt/context engineering... any proven experience there ? a public portfolio ? and i am sorry, but it does not seem feasible you can afford pets currently...

slipwalker

16 giorni fadiscuss

towards system design and solution architecture.

slipwalker

17 giorni fadiscuss

for my needs, raycast suffices, and it is one less app to install.

slipwalker

17 giorni fadiscuss

homebrew ( indispensable ! all the other apps below are installed/managed via homebrew ):

- raycast ( keyboard shortcuts for clipboard manager, basic window management, pomodoro tracking and app launch )

- stats

- ice ( menubar manager )

- theBoringNotch ( to have some use for the annoying notch )

- mole ( storage cleaner )

- wezterm ( inside which i run zsh, tmux, neovim, zoxide, eza, batcat, ripgrep, fzf, fdfind, yazi, btop, lazygit, lazydocker... )

- textmate

- iina

- zen browser ( with uBlock origin and betterfox settings )

slipwalker

22 giorni fadiscuss

i have toyed around Tiny Llama 1.1B ( https://github.com/jzhang38/TinyLlama ) for the "conversational brain" of NPCs in a game i was dabbling.... it was fun.

slipwalker

23 giorni fadiscuss

drop horizontal layers architectures and focus on vertical-slices. This alone reduces the needed context window per feature by an order of magnitude.

slipwalker

28 giorni fadiscuss

Role playing… it’s basically lying and pretending with extra steps.

slipwalker

29 giorni fadiscuss

multiple pi.dev with opencode.ai/go plan; inside herdr muxer.

works nicely at a very agreeable cost ( USD$10/mo ).

slipwalker

30 giorni fadiscuss

how about opencode's go ( https://opencode.ai/go ) it is very cost effective and the models are surprisingly competent....

slipwalker

2 mesi fadiscuss

just out of curiosity, which GPU are you running on your local machine ?

slipwalker

2 mesi fadiscuss

https://opencode.ai/en/go

evaluate the Opencode's budget friendly "Go plan"

slipwalker

2 mesi fadiscuss

ship it !

slipwalker

2 mesi fadiscuss

are you using opencode ?

slipwalker

2 mesi fadiscuss

Elite (1984) used procedural generation to create EIGHT entire galaxies, each with 256 star systems, on a floppy disk that was less than 48 kilobytes!

slipwalker

2 mesi fadiscuss

i like opencode's zen https://opencode.ai/en/zen with opencode's TUI.

slipwalker

3 mesi fadiscuss

maybe this: https://www.skillsdirectory.com/ ?

comments