Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Show HN: Ggplot2 chart playground – in the browser with WebAssembly
(github.com/QuesmaOrg)
4 points
stared
9 months ago
discuss
2.
▲
We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them
(quesma.com)
245 points
jakozaur
3 months ago
98 comments
3.
▲
Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22%
(quesma.com)
197 points
blndrt
9 months ago
65 comments
4.
▲
The security paradox of local LLMs
(quesma.com)
160 points
jakozaur
7 months ago
87 comments
5.
▲
CompileBench: Can AI Compile 22-year-old Code?
(quesma.com)
148 points
jakozaur
8 months ago
65 comments
6.
▲
Benchmarking OpenTelemetry: Can AI trace your failed login?
(quesma.com)
144 points
stared
4 months ago
79 comments
7.
▲
Show HN: Reviving a 20-year-old puzzle game Chromatron with Ghidra and AI
(quesma.com)
28 points
stared
3 months ago
9 comments
8.
▲
Tau² Benchmark in Action: Early Results and Key Takeaways
(quesma.com)
16 points
luciesim
9 months ago
discuss
9.
▲
Outside of the bubble, AI is Black Mirror
(quesma.com)
7 points
stared
6 months ago
discuss
10.
▲
We hid backdoors in binaries – Opus 4.6 found 49% of them
(quesma.com)
6 points
stared
4 months ago
2 comments
11.
▲
Prompts are (not) the new source code
(quesma.com)
6 points
stared
5 months ago
1 comment
12.
▲
Migrating CompileBench to Harbor: standardizing AI agent evals
(quesma.com)
6 points
stared
5 months ago
discuss
13.
▲
A postmortem on our $2.5M database gateway: lessons from pilot purgatory
(quesma.com)
6 points
jakozaur
7 months ago
discuss
14.
▲
Don't Let Apache Iceberg Sink Your Analytics: Practical Limitations in 2025
(quesma.com)
6 points
jakozaur
a year ago
discuss
15.
▲
ClickHouse Cloud Pricing Change in January 2025: A Price Hike with Many Tweaks
(quesma.com)
6 points
jakozaur
a year ago
discuss
16.
▲
We hid backdoors in binaries – Opus 4.6 found 49% of them
(quesma.com)
5 points
stared
4 months ago
2 comments
17.
▲
Nano Banana Pro: raw intelligence with tool use
(quesma.com)
5 points
stared
6 months ago
2 comments
18.
▲
AI for coding is still playing Go, not StarCraft
(quesma.com)
5 points
stared
8 months ago
2 comments
19.
▲
OTelBench: Can AI instrument OpenTelemetry?
(quesma.com)
5 points
jakozaur
4 months ago
1 comment
20.
▲
Building Grafana dashboards with AI, CLI and a bit of pragmatism
(quesma.com)
5 points
stared
a year ago
1 comment
21.
▲
Show HN: 60-Second Linux Analysis, Supercharged with Nix and LLMs
(quesma.com)
4 points
piotrgrabowski
9 months ago
1 comment
22.
▲
Benchmarking OpenTelemetry: Can AI trace your failed login?
(quesma.com)
4 points
stared
4 months ago
discuss
23.
▲
Nano Banana Pro: raw intelligence with tool use
(quesma.com)
4 points
jakozaur
6 months ago
discuss
24.
▲
Sandboxing AI-Generated Code: Why We Moved from WebR to AWS Lambda
(quesma.com)
4 points
stared
10 months ago
discuss
25.
▲
Compare harnesses not models: Blitzy vs. GPT-5.4 on SWE-Bench Pro
(quesma.com)
3 points
stared
2 months ago
discuss
26.
▲
Reverse Engineering River Raid with Claude, Ghidra, and MCP
(quesma.com)
3 points
stared
4 months ago
discuss
27.
▲
Reverse Engineering River Raid with Claude, Ghidra, and MCP
(quesma.com)
3 points
stared
4 months ago
discuss
28.
▲
Nano Banana Pro: raw intelligence with tool use
(quesma.com)
3 points
amrrs
6 months ago
discuss
29.
▲
We raised $2.5M for a database gateway and failed: Postmortem
(quesma.com)
3 points
groseje
7 months ago
discuss
30.
▲
Claude Code + OpenTelemetry + Grafana: A guide to tracking usage and limits
(quesma.com)
3 points
stared
10 months ago
discuss
More