@Patrity

🔨Building https://nitter.cf/t.co/55txChcWuT @ThundoriaGame https://nitter.cf/t.co/7NVd52luIb

 Southeast Texas, United States
patrity.com
Joined June 2012
  • Tweets939
  • Following115
  • Followers1.9K
148Media
I really hope Opus stops explaining everything to ridiculous levels and stops talking to me like I'm British. So sick of it "optimising" everything and talking about "colours"
Claude
@claudeai
Sep 22
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
2
58
Finally hit 192gb vram for local AI! Welcome home sweet, sweet RTX Pro 6000 600w! #homelab #localai #ai
2
80
My self-hosted AI coding stack processed 6.7 billion tokens since April. Electricity bill: $35.85. Same tokens at cloud API rates: ~$961. 27x cheaper, fully metered.. GPU power draw + throughput wired into LiteLLM so every request gets a real price tag.
1
4
80
Full writeup: the measurement methodology, where all 6.7B tokens actually went, and the LiteLLM spend-table traps I hit backfilling the history techhivelabs.net/blog/local-…

Local LLM Cost Analysis: Electricity per Token vs the Cloud

My friends said the new model on my rig was drunk. Root-causing that from LiteLLM request logs turned into pricing every token my GPUs have ever produced.. and a $961 cloud comparison.

techhivelabs.net
2
30
I haven't been posting a ton about my progress on @ThundoriaGame but I am pretty proud of this feature. Fully procedurally generated mines. A room created per "floor" and an inventory system that forces players to make tough choices at the end of each floor!
2
103
Is it cool? I think so! Is it useful, yes! This is just the start to my self-hosted homelab agent build out. This is a custom Nuxt JS application using Three.js to render and react to audio. It passes through three locally hosted models: open ai whisper v3 -> qwen3.6 35b a3b -> kokoro 82m. Exposes tools to search my knowledge base and memory along the way. Here is Bridget introducing herself to a friend from Discord.
3
64
Ran Qwen3.6 27B dense vs 35B-A3B MoE on two 3090s expecting the dense flagship to win. It lost by 4 SWE-bench points and won everything else: 5.5x faster prefill, 2.5x the context, tied on every hard task I gave it by hand. Benchmarks measure the limit. You live in the middle.
1
3
73
Full writeup with reproducible vLLM commands and the gotchas that cost me hours (the mamba-cache crash, the "24GB is a lie" vision-encoder OOM): techhivelabs.net/blog/local-…

Qwen3.6 27B Dense vs 35B-A3B MoE on Dual RTX 3090 (vLLM Benchmarks)

I finally got Qwen3.6 running locally, ran the dense flagship against the sparse MoE, and learned that four benchmark points are worth a lot less than 5x prefill.

techhivelabs.net
2
61
Honestly for me, one of my favorite part of #GameDev is building my own tools and getting it working how I want. This is an animation editor I made for 2d sprite sheet animations for my game. Exports clean json to load in @phaser_ #IndieGames #PixelArt #GameDevelopment
1
2
31
1,509
Probably shouldn't have built my entire asset pipeline before getting y-sorting properly setup. BUT I'm glad I got it done. Tiled editor did help a ton and the first-class @phaser_ integration with Phaser honestly made it not too bad!
1
4
339
found out today that one of my hermes cron jobs has been firing every 2 hours for a week.. against a model that no longer exists.. and my dashboard logged 'ok' every single time. 36 consecutive 'ok's for a request the proxy never answered. my robots are gaslighting me.
1
26
ok so I built codethis.dev it's a paste bin where every paste is also a carbon-style code screenshot AND a doc you can render with markdown components (Nuxt MDC).. and the MCP server is free forever so claude can write to it directly from your IDE. 🧵a thread on the why
1
2
162
more replies
things I will not pretend codethis is great at: - no git history per paste (gist still wins on that).. yet - no line-highlighting on the image export (carbon still wins there) - the brand is at zero -- you have never heard of this. that is what today is for. shipping more in the next few weeks.
1
24
pricing - free forever covers everything that makes this useful: paste, markdown, image export, MCP server, REST API, 100+ langs, 2 API keys. pro is $9/mo and unlocks password-protected pastes, private pastes, watermark removal, scale, 20 API keys. the wedge is free. it stays that way.
56
shipping a paste tool tomorrow. the kind of side project that takes six years to build ..if you count the hastebin fork I ran since 2020, which I do, because it is the only honest way to count it. No login needed, free API/MCP, image generation, the works. codethis.dev

Not your average paste bin — CodeThis

Rich markdown, 100+ languages, beautiful by default. Share code and documentation with custom MDC components.

codethis.dev
1
78
If you could stop exposing me, @WakaTime , that would be great 🤣😭
2
60
Load more