Search: github.com/mudge | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

91.

Composo open-sources its LLM-as-Judge technique (83.6% on RewardBench 2)

github.com/composo-ai

3 months ago

5 points

92.

Show HN: Open-source expense and budget tracker with SQL API for AI agents

github.com/kirill-markin

4 months ago

3 points

93.

github.com/g0v-it

5 years ago

3 points

94.

Awesome-LLM-Judges

github.com/haizelabs

a year ago

2 points

95.

github.com/haizelabs

a year ago

2 points

96.

UVa Online Judge Solutions Repo (Work in Progress)

github.com/jcbages

9 years ago

2 points

97.

Stack on a Budget – A collection of services with great free tiers

github.com/255kb

10 years ago

156 points

98.

Stack on a Budget (Free Tier Driven Development FTDD)

github.com/255kb

8 days ago

3 points

99.

Show HN: Lightweight LLM-as-a-Judge Tool

github.com/frequena

10 months ago

2 points

100.

Collection of services with great free tiers

github.com/255kb

10 years ago

1 points

101.

Keeping multimodal parsing free for all

a year ago

3 points

102.

Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost

3 months ago

2 points

103.

12 years ago

2 points

104.

The Divine Judgement: Enforce TypeScript Types at Runtime

github.com/Divine-Software

3 years ago

1 points

105.

Performance Budgets (Budget.json)

github.com/GoogleChrome

4 years ago

1 points

106.

Show HN: Guitos, a free open-source budgeting app

3 years ago

53 points

107.

Ranking 1k ShowHN posts by estimated merit using an LLM judge and TrueSkill

github.com/kouhxp

a month ago

7 points

108.

Show HN: Tokencap – Token budget enforcement across your AI agents

github.com/pykul

3 months ago

7 points

109.

Ratchets: a Rust tool that polices style violations with a flexible budget

github.com/imbue-ai

7 days ago

5 points

110.

Show HN: TUI personal monthly budget planner

github.com/eliasdorneles

a year ago

4 points

111.

Type-challenges: Collection of TypeScript type challenges with online judge

github.com/type-challenges

3 years ago

4 points

112.

Raspberry Pi-Based Personal Productivity Nudger

github.com/edmarkovich

6 years ago

4 points

113.

LoCoMo AI Benchmark: 6.4% of answer key wrong, judge accepts 63% of fake answers

github.com/dial481

3 months ago

3 points

114.

Show HN: Using AI to judge a drinking game – SplitTheG.dev

a year ago

3 points

115.

Show HN: Signals – finding the most informative agent traces without LLM judges

3 months ago

3 points

116.

Show HN: Claude Gym – a tiny CLI that nudges you to move while Claude Code runs

4 months ago

3 points

117.

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget

github.com/SonyResearch

a year ago

3 points

118.

Justice: Yet Another Online Judge

7 years ago

3 points

119.

Show HN: Grading Notes for LLM-as-Judge

github.com/shabie

2 years ago

2 points

120.

MartinLoop – budget caps and audit trails for AI coding agents

github.com/Keesan12

a month ago

2 points