Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Token Efficiency
Clear
Titles
Summaries
6
ALTK-Evolve Outperforms ACE Agent Memory System at 40% of Token Cost on AppWorld Benchmark
Research
1
Aug 11
6
ALTK-Evolve Outperforms ACE Agent Memory System at 40% of Token Cost on AppWorld Benchmark
Research
· 1 src · Aug 11
Discuss
6
Research: Structured Distillation Cuts AI Agent Memory Tokens 11× While Preserving Retrieval Accuracy
Research
1
Aug 6
6
Research: Structured Distillation Cuts AI Agent Memory Tokens 11× While Preserving Retrieval Accuracy
Research
· 1 src · Aug 6
Discuss
6
LangChain Ships Deep Agents v0.7 with 65% Fewer Base Input Tokens
Products
1
Jul 29
6
LangChain Ships Deep Agents v0.7 with 65% Fewer Base Input Tokens
Products
· 1 src · Jul 29
Discuss
6
Agent Skill "Compilation" Cuts Token Use 94% and Latency 87% by Replacing LLM Steps with Code
Research
1
Jul 15
6
Agent Skill "Compilation" Cuts Token Use 94% and Latency 87% by Replacing LLM Steps with Code
Research
· 1 src · Jul 15
Discuss
7
Empirical Study: Claude Code Sends 33K Tokens Before Reading the Prompt — 4.7× More Than OpenCode
Products
1
Jul 13
7
Empirical Study: Claude Code Sends 33K Tokens Before Reading the Prompt — 4.7× More Than OpenCode
Products
· 1 src · Jul 13
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
