Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Show HN: I open-sourced a $1M engine for closing loops in embedding space
(github.com/onestardao)
8 points
WFGY
a year ago
10 comments
2.
▲
Show HN: AGI Lite for Free,Semantic AI boost with WFGY(stability ×3.6, open SDK
(github.com/onestardao)
2 points
PSBigBig
a year ago
1 comment
3.
▲
Show HN: WFGY – A reasoning engine that repairs LLM logic without retraining
(github.com/onestardao)
11 points
WFGY
a year ago
6 comments
4.
▲
Show HN: TXT OS – Open-Source AI Reasoning, One Plain-Text File at a Time
(github.com/onestardao)
10 points
TXTOS
a year ago
6 comments
5.
▲
Show HN: WFGY – Endorsed by Tesseract.js dev, 2k+ downloads/month live
(github.com/onestardao)
7 points
TXTOS
10 months ago
3 comments
6.
▲
Show HN: Achieves Perfect 100 Score Across 6 Leading AI Model Evaluations
(github.com/onestardao)
6 points
TXTOS
a year ago
8 comments
7.
▲
Show HN: Subtle Failure Modes I Keep Seeing in Production‑Grade AI Systems
(github.com/onestardao)
6 points
TXTOS
10 months ago
2 comments
8.
▲
Show HN: A tiny reasoning layer that steadies LLM outputs (MIT; +22.4% accuracy)
(github.com/onestardao)
6 points
TXTOS
10 months ago
discuss
9.
▲
Show HN: 70 days, 800 stars. If AI bugs are not random but math inevitable?
(github.com/onestardao)
5 points
tgrrr9111
9 months ago
1 comment
10.
▲
Show HN: Txtos for LLMs – 60 SEC setup, long memory, boundary guard, MIT
(github.com/onestardao)
5 points
tgrrr9111
9 months ago
1 comment
11.
▲
Show HN: 70 Days → 800 GitHub Stars (Cold Start) – My Secret Was a Problem Map
(github.com/onestardao)
5 points
tgrrr9111
9 months ago
1 comment
12.
▲
We open-sourced a 'Semantic Clinic' for LLM bugs – 16 root causes
(github.com/onestardao)
4 points
TXTOS
10 months ago
1 comment
13.
▲
Show HN: I made a semantic OS for language reasoning (not kidding)
(github.com/onestardao)
3 points
TXTOS
10 months ago
discuss
14.
▲
Show HN: "hard questions" as a shared language for cross-domain reasoning
(github.com/onestardao)
2 points
wfgy-github
4 months ago
discuss
15.
▲
Show HN: A text-only reasoning core for LLMs (MIT, system prompt and self-test)
(github.com/onestardao)
1 point
wfgy-github
4 months ago
discuss