Oh this is going to blow up
Hey folks I am a synthetic immunologist / physician scientist who loves to create stuff and I am so excited about LLMs.
I want to meet remarkable people so please say hi.
Here I coin the term “Transformer Paleophobia”
It defines the distress LLM folks experience when they see somebody using an old model or a technology.
Examples:
Normie: “I downloaded llama 3 and it works without internet!”
Transformer Paleophobic: “you gotta use qwen3.5 9B! It also fits and is much better!”
Normie: “I hate ChatGPT when it thinks”
TP: “actually thinking more is better 😭”
Normie: “they don’t let me pick gpt-4o anymore”
TP: “😭😭😭😭😭😭😭”
@LottoLabs I am going to coin a new term where local llm guys getting mad at people who mention a 6 month old model or god forbid llama 3.1 or something 😃
Two Mac Studios, M3 ultra 256GB - what do you want to test?
I will be testing various strong models:
Minimax 2.7
Deep seek V4 Flash
Gemma 4 31B
Qwen3.6 27B
Qwen 3.5 122B A10B
MLX vs GGUF
0 context vs 10K context
Prompt caching vs no caching
Testing: TTFT and T/S
@fabianstelzer I actually built that into my own app where users have an agent via sms - agent knows the time of all messages and it’s brilliant - no issues whatsoever