Search: github.com/jbenc | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

Show HN: Deepcon – Get the most accurate context for coding agents

8 months ago

7 points

152.

Show HN: Semble – Fast code search for agents with near-transformer accuracy

github.com/MinishLab

2 months ago

7 points

153.

Show HN: LLM Tree Navigation Benchmark

github.com/aiwebb

2 years ago

6 points

154.

Show HN: ML-Dev-Bench – Benchmarking AI Agents on Real-World AI Workflows

github.com/ml-dev-bench

a year ago

6 points

155.

Ask HN: Vector-space database (as a service)?

9 years ago

5 points

156.

Show HN: BustAPI – A Python framework with a Rust core claiming 50x Flask speed

github.com/GrandpaEJ

6 months ago

5 points

157.

The world's fastest Objective-C JSON serializer/deserializer

15 years ago

5 points

158.

My GLM-5.1 coding agent scored 94.3% on LiveCodeBench Lite (348/369)

2 months ago

5 points

159.

Show HN: I benchmarked LLM agents on fixing real-world security vulnerabilities

giovannigatti.github.io

18 days ago

4 points

160.

Show HN: SGR – A Linear-Complexity "Living Cell" Outperforming Transformers

5 months ago

4 points

161.

Show HN: Machine Learning on JVM or a piece of cake

8 years ago

4 points

162.

Show HN: Isolated benchmarks to avoid optimization pollution (Node.js)

github.com/Llorx

5 months ago

3 points

163.

Show HN: Gemini 2.5 is the best model for Kotlin and Android dev

a year ago

aman-firebender

3 points

164.

Show HN: JStachio a type-safe Mustache engine that is incredible fast

github.com/jstachio

3 years ago

3 points

165.

Show HN: SQL++ – 5x faster than Prisma (Rust)

github.com/sinisterMage

7 months ago

2 points

166.

Show HN: A benchmark for SAST exploit chain and evasion detection

github.com/TheAuditorTool

2 months ago

2 points

167.

Measuring the actual power draw of Teams, Meet, Discord, Slack and Zoom

3 months ago

2 points

168.

Show HN: Repid v2 – open-source async Python task queue with AsyncAPI docs

2 months ago

2 points

169.

Show HN: PyNear – exact and approximate KNN, faster than Faiss

3 months ago

2 points

170.

Show HN: I made web agents reliable with smaller LLMs via natural language

github.com/nottelabs

a year ago

2 points

171.

Benchmark of ZKVM and Proving Schemes

2 years ago

1 points

172.

ARCHE3-7B – Sparse Moe with SmartRouter and Foundation Curriculum Training

3 months ago

OpenSynapseLabs

1 points

173.

Show HN: Sediment – Local semantic memory for AI agents (Rust, single binary)

github.com/rendro

4 months ago

1 points

174.

Show HN: I made a site with current and predicted Apple M processor benchmarks

rubjo.github.io

a year ago

1 points

175.

Microsoft forked MIT licensed repo and changed the copyright [fixed]

github.com/microsoft

4 years ago

1326 points

176.

gRPC benchmark results

github.com/LesnyRumcajs

5 years ago

217 points

177.

Benchmark Framework Desktop Mainboard and 4-node cluster

github.com/geerlingguy

10 months ago

203 points

178.

Speech-to-Text Benchmark: Framework for benchmarking speech-to-text engines

github.com/Picovoice

8 years ago

195 points

179.

Single Board Computers Benchmarks

github.com/ThomasKaiser

4 years ago

144 points

180.

How much bandwidth does the L2 have to give, anyway?

github.com/travisdowns

8 years ago

143 points