architect/programmer. SNES-game genie, rock n roll racing, wing commander, etc. NN programming and architecture these days.
Joined December 2021
- Tweets 1,246
- Following 524
- Followers 457
- Likes 189,351
7 Photos and videos
Apr 2
if you haven't seen it yet, shrike labs just came out with a DC based power supply system for home / dev labs. Extremely cool stuff. youtube.com/watch?v=Ig7oZpuj…
1
20
Feb 17
anyone else's isp getting salty about the amount of 600gb downloads and uploads we have to do for large models? i'm at 10tb for the month and climbing.
1
50
Jan 12
everyone should have their own local AI setup with multiple models for various things. Dense and thinking models and 400gb sizes are best. MOE models with huge training sets are great too. Lastly, don't forget to have vision and listening models.
2
46
15 Nov 2025
There is so much AI slop out there that I am seriously thinking about writing something that lets us humans tag it and avoid it.
2
7
317
dotNET blog: How Copilot Studio uses .NET and WebAssembly for performance and innovation ift.tt/Um4NSCt
1
6
43
2,874
Allen retweeted
3 Nov 2025
Entity Framework 10 breaking changes ⚠️
#dotnet
learn.microsoft.com/en-us/ef…
2
13
108
13,110
26 Oct 2025
Session based auth is safer and easier than JWT for auth that doesn't need SSO. The server side db cache lift is minimal compared to the safety and simplicity benefit. Change my mind.
1
130
23 Oct 2025
maybe the best model isn't a mixture of experts but rather a mixture of competing / contrarian experts? but how do you get to intellectual honesty / integrity for a solution? MOE depends on a supposed expert choice. @xai
152
20 Oct 2025
var in C# was a mistake; explicit types forced developers to understand and intentionally use specific types. Change my mind.
1
1
131
13 Oct 2025
I just tried mint linux and must say I'm pretty impressed. I've been a linux hater for a long time but this might actually get me to use it more for a desktop.
1
120
22 Sep 2025
This is just my theory but I think LLMs struggle with debugging because they're trained on final results, not the process to reach them.
3
152
9 Sep 2025
Programmed a c# class without any AI code gen yet again. Only asking AI questions. Infinitely faster than trying to #vibecode some abomination from scratch.
4
197
16 Aug 2025
most don't realize how much overhead LLM APIs like OpenAI's have in streaming mode—95% of the traffic is just JSON wrappers around each tiny token. Experimenting with direct gRPC binary comms on my setup to slash that inefficiency.
2
610
16 Aug 2025
is it just me or are there literally no good desktop based email apps right now?
1
4
518
15 Aug 2025
vibe coding is such a joke. Even having AI write a lot of code for you just makes it all take longer. Ask AI questions instead of having to google for it and you'll have much better results.
3
2
6
584
1 Aug 2025
If your kilo code setup is failing to index a workspace, check the vector db dimensions for mismatches.
1
4
338
28 Jul 2025
ok fine, I created an #mcpserver router discovery protocol. Setting up new mcp servers is a huge PITA and this makes it easy.
157
16 Jul 2025
NNs graphrag context are instance dungeons in WoW. It all comes together but you still need facts / crystalized knowledge lookup. This is not a math problem, its a logic problem.
179