Hacker News new | ask | show | jobs
user: dotnot
created: 2026-02-22
karma: 2

submissions:

Why LLMs will be always Terrible at Software Architecture
3 points | 0 comments
LLM Terminology explained simply: Weights, Inference, Effective sequence length
5 points | 1 comments
0 points | 0 comments
Real-world GPT-OSS-20B benchmark on L4, L40S and H100 (latency, tokens/SEC)
1 points | 0 comments