HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
31.
▲
Show HN: LLM Thematic Generalization Benchmark
github.com/lechmazur
discuss
a year ago
zone411
6 points
32.
▲
LLM Confabulation (Hallucination) Leaderboard
github.com/lechmazur
discuss
2 years ago
zone411
6 points
33.
▲
Elimination Game: Multi-Agent LLM Social Reasoning, Strategy, and Deception
github.com/lechmazur
discuss
a year ago
zone411
5 points
34.
▲
Show HN: LLM Creative Story-Writing Benchmark
github.com/lechmazur
discuss
a year ago
zone411
5 points
35.
▲
RootAsRole: A secure alternative to sudo/su using principle of least privilege
github.com/LeChatP
discuss
3 years ago
sbt567
5 points
36.
▲
Nff_: Open-source Claude Code for hardware
github.com/GLechevalier
discuss
4 hours ago
GL26
3 points
37.
▲
Show HN: LLM Sycophancy Benchmark: Opposite-Narrator Contradictions
github.com/lechmazur
discuss
3 months ago
zone411
3 points
38.
▲
Freebind: An IPv6 address rate limiting evasion tool (that also supports IPv4)
github.com/blechschmidt
discuss
2 years ago
ocean_moist
3 points
39.
▲
Pix2tex – LaTeX OCR
github.com/lukas-blecher
discuss
4 years ago
marcodiego
3 points
40.
▲
Minimal and beautiful theme for the GNOME Desktop Environment
github.com/hdni
2 comments
12 years ago
grigio
2 points
41.
▲
I took the le chaton fat AI model meme a step further by making a model
github.com/princezuda
1 comment
6 days ago
zuda
2 points
42.
▲
RootAsRole – A better alternative to sudo(-rs)/su
github.com/LeChatP
discuss
2 months ago
p4bl0
2 points
43.
▲
Show HN: A vibe-coded low-level PKCS#11 Terraform provider
github.com/blechschmidt
discuss
4 months ago
blechschmidt
2 points
44.
▲
Elimination Game Benchmark: Social Reasoning, Strategy, and Deception in LLMs
github.com/lechmazur
discuss
a year ago
amichail
2 points
45.
▲
Step-Game: Assessing LLM Collaboration and Deception Under Pressure
github.com/lechmazur
discuss
a year ago
amichail
2 points
46.
▲
OpenUDID - Opensourced UDID replacement
github.com/ylechelle
discuss
15 years ago
BenSS
2 points
47.
▲
Accurately calculating the number of legal chess positions
github.com/lechmazur
discuss
5 years ago
slyall
2 points
48.
▲
LLM Position Bias Benchmark: Swapped-Order Pairwise Judging
github.com/lechmazur
discuss
2 months ago
zone411
1 points
49.
▲
Benchmark that evaluates LLMs using 759 NYT Connections puzzles
github.com/lechmazur
discuss
6 months ago
ShrugLife
1 points
50.
▲
NYT Connections LLM Benchmark
github.com/lechmazur
discuss
6 months ago
cainxinth
1 points
51.
▲
Show HN: LLM UI Challenge
github.com/alechewitt
discuss
6 months ago
alechewitt
1 points
52.
▲
Mathias Lechner
github.com
discuss
2 years ago
rolph
1 points
53.
▲
FizzBuzzLang – the programming language no one asked for
github.com/lechien73
discuss
6 years ago
shever
1 points
54.
▲
Logo comment – generate logos for source code comments
github.com/alechewitt
discuss
11 years ago
alechewitt1
1 points
55.
▲
Clifm 1.17 (Lechuck) is out!
github.com/leo-arch
1 comment
2 years ago
archcrack
1 points
56.
▲
Show HN: Open-source Canadian COVID-19 bot
1 comment
6 years ago
lecha
6 points
57.
▲
PINCE – A GDB front-end/reverse engineering tool focused on games
github.com/korcankaraokcu
3 comments
10 years ago
blechschmidt
93 points
58.
▲
Replay server responses from a HAR file
github.com/Stuk
discuss
11 years ago
lechevalierd3on
7 points
59.
▲
Show HN: Rpmrepo-update – Incremental RPM repo updates for S3 (no full sync)
github.com/e2llm
1 comment
6 months ago
Alechko
2 points
60.
▲
Curated LLM prompts for debugging with runtime DOM snapshots
github.com/e2llm
1 comment
10 months ago
Alechko
2 points
More