letsdatascience

Daytona Raises $60M for Agent Cloud Infrastructure

Daytona raised a $60 million Series B at a $1 billion valuation on October 20, becoming Croatia's third unicorn, according to ...

同じ問題を解決してもAIによってコードの増加量に大きな差、AI ...

AIがプログラムを修正する際に追加したコードと削除したコードの差を測定するオープンソースのベンチマーク「Parsimony」が公開されました。従来のベンチマークで重視されてきた問題の解決率やコストに加えて、コードの増加量からAIモデルを比較できるのが特徴です。
Security Boulevard

Bright Security Introduces STAR Fuzzer, Agentic Fuzzing That Writes Its Own Harnesses and ...

Home » Security Bloggers Network » Uncategorized » Bright Security Introduces STAR Fuzzer, Agentic Fuzzing That Writes Its ...
MarkTechPost

Google Open-Sources Harness2, a Recursive Agent Harnessing Framework

Google open-sourced Harness2, a recursive agent harnessing framework that lifted GLM-5 11.5 points on WorkBuddy-Bench with ...

Just Splitting Mahjong Tiles Leads to a Massive Flowchart—The Invention of Recursive ...

When studying programming, you notice something strange.Processes that are extremely complex for humans to think through can ...

[Sieve-Core] Deterministic Structural Aggregation via Tarjan's Strongly Connected ...

Extracting from structure rather than generating informationThe amount of information on the internet continues to ...
HackerNoon

Matryoshka RLM Tested: Can Coding Agents Query Huge Files Without RAG?

I drove its lattice-mcp tools by hand from a TypeScript client, checked every answer against grep, and hit five gotchas.
How-To Geek on MSN

Stop using grep, these 5 modern replacements do everything better

See how modern search utilities add fuzzy matching, context highlights, and configurable result pipelines for speed.
MarkTechPost

Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitting

Google Research open-sources RRSI, letting agents improve prompts, tools and memory without overfitting, lifting Terminal-Bench 2.1 to 80.2%.
腾讯网

Claude Code、Codex组队干活，Raven新版本既做总调度，也让Harness持续进化

导读｜RSI（递归自我改进）不应只发生在模型参数层：类比人类大脑的不是 LLM，而是整个 Agent。EverMind 开源的 Raven V0.2.0 为此提供了两个核心设计：为 RSI 而设计的 Harness 框架，以及统一编排专业 Agent 的 The Harness of Harnesses。在多 Agent 编排、深度研究、编码、设计与持续执行评测中，Raven 的多项结果优于同底座 ...