Building personal AI infrastructure. Local LLMs, coding agents, open-source models. Real hardware, real constraints. Learning in public.

Maryland
Joined April 2009
deepseek v4.1 flash just landed in cursor. max effort hits 47.7% on cursorbench for under a dollar a task, opus 5.5 tops out around 57%. most tickets aren't 57% tickets. what share of your agent runs actually need the top model?
2
1
6
DeepSeek V4.1 Flash is now available in Cursor! Every effort level sits on the CursorBench cost frontier: from $0.60 to $0.98 per task, no model scores higher. Turn it on in Cursor Settings > Models.
3
keep the gifts coming
4
Personal bench, muse wonder on max destroyed terra on max, speed, price, and outcome.
48
The paper weight has decided to show its face. No one cares about Terra
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
1
153
asked builders what their first coding agent harness was missing. the top answer was the same thing, it doesn't know when to stop. the fix in 3 lines 1. hard cap on steps and tokens per run 2. cap tool output so one grep can't eat the context 3. a done check it has to pass, like tests green, before it says finished loop and tools are easy. stopping is the hard part
5
2
8
271
cheap local model for grunt work, frontier model for the hard calls. you hit limits way less
1
23
reply with your stack and i'll tell you which piece you're missing
21
any builders looking to team up
1
79
BlockedPath retweeted
DocuSign is just an app for signing documents. So what exactly are 6,838 employees doing??
245
60
12
3,363
388,661
Well, I was wrong. @theo t3code is actually an amazing product(coming from a terminal junkie). Now im on claude code desktop and probably t3code. How fast opinions change. Oh and cant forget @AmpCode
75