Y
Hacker News
new
|
ask
|
show
|
jobs
user:
sebastianperezr
created:
2026-04-24
karma:
4
submissions:
AI Agents Show Long Context Gains with LCM, Specialized Applications Emerge
2 points
|
0 comments
LLM Inference Throughput Rises 4.5x with Parallel Verification
2 points
|
0 comments
Anthropic NLAs translate LLM activations to human-readable text for safety
1 points
|
0 comments
Canvas Data Breach; DeepSeek V4 Flash Boosts LLM Inference 4.3x
2 points
|
0 comments
0 points
|
0 comments