Search: quesma.com | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: Ggplot2 chart playground – in the browser with WebAssembly

github.com/QuesmaOrg

9 months ago

4 points

2.

We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

4 months ago

245 points

3.

Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22%

9 months ago

197 points

4.

The security paradox of local LLMs

8 months ago

160 points

5.

CompileBench: Can AI Compile 22-year-old Code?

9 months ago

148 points

6.

Benchmarking OpenTelemetry: Can AI trace your failed login?

5 months ago

144 points

7.

Show HN: Reviving a 20-year-old puzzle game Chromatron with Ghidra and AI

4 months ago

28 points

8.

Tau² Benchmark in Action: Early Results and Key Takeaways

10 months ago

16 points

9.

Outside of the bubble, AI is Black Mirror

7 months ago

7 points

10.

We hid backdoors in binaries – Opus 4.6 found 49% of them

4 months ago

6 points

11.

Prompts are (not) the new source code

5 months ago

6 points

12.

Migrating CompileBench to Harbor: standardizing AI agent evals

6 months ago

6 points

13.

A postmortem on our $2.5M database gateway: lessons from pilot purgatory

8 months ago

6 points

14.

Don't Let Apache Iceberg Sink Your Analytics: Practical Limitations in 2025

a year ago

6 points

15.

ClickHouse Cloud Pricing Change in January 2025: A Price Hike with Many Tweaks

a year ago

6 points

16.

We hid backdoors in binaries – Opus 4.6 found 49% of them

4 months ago

5 points

17.

Nano Banana Pro: raw intelligence with tool use

7 months ago

5 points

18.

AI for coding is still playing Go, not StarCraft

8 months ago

5 points

19.

OTelBench: Can AI instrument OpenTelemetry?

5 months ago

5 points

20.

Building Grafana dashboards with AI, CLI and a bit of pragmatism

a year ago

5 points

21.

Show HN: 60-Second Linux Analysis, Supercharged with Nix and LLMs

10 months ago

4 points

22.

Benchmarking OpenTelemetry: Can AI trace your failed login?

5 months ago

4 points

23.

Nano Banana Pro: raw intelligence with tool use

7 months ago

4 points

24.

Sandboxing AI-Generated Code: Why We Moved from WebR to AWS Lambda

10 months ago

4 points

25.

Compare harnesses not models: Blitzy vs. GPT-5.4 on SWE-Bench Pro

2 months ago

3 points

26.

Reverse Engineering River Raid with Claude, Ghidra, and MCP

5 months ago

3 points

27.

Reverse Engineering River Raid with Claude, Ghidra, and MCP

5 months ago

3 points

28.

Nano Banana Pro: raw intelligence with tool use

7 months ago

3 points

29.

We raised $2.5M for a database gateway and failed: Postmortem

8 months ago

3 points

30.

Claude Code + OpenTelemetry + Grafana: A guide to tracking usage and limits

a year ago

3 points