Search: github.com/haltu | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Halgorithem – Catching AI Hallucinations Using Trees, No AI in Pipeline (github.com/TangibleResearch)

5 points

22 days ago

62.

Microsoft's prompts that turn GPT into Bing revealed (or hallucinated?)

5 points

3 years ago

63.

Show HN: Judicex – Open-source legal AI that abstains instead of hallucinating (github.com/JustVugg)

5 points

10 days ago

64.

Zero-hallucination knowledge engine – LLM never reasons, graph does all the work (github.com/skvcool-rgb)

4 points

2 months ago

65.

Show HN: I built a 0.07ms Python firewall to stop AI hallucinations

4 points

2 months ago

66.

Authors claim they just figured out how to predict LLM hallucinations (github.com/leochlon)

4 points

9 months ago

67.

A thermodynamic trust layer cutting LLM hallucinations by 52% (github.com/Dan23RR)

4 points

a month ago

68.

Endless Wiki – A useless self-hosted encyclopedia driven by LLM hallucinations (github.com/XanderStrike)

4 points

9 months ago

69.

Show HN: Detecting hallucinations in LLM function calling with entropy (archgw.com)

4 points

honorable_coder

10 months ago

70.

Open source library to find hallucinations and ground your LLM (github.com/dioptra-ai)

4 points

3 years ago

71.

High rate of LLM (GPT5) hallucinations in dense stats domains (cricket)

3 points

9 months ago

72.

Show HN: UQLM – Closed-book hallucination detection with UQ (github.com/cvs-health)

3 points

4 days ago

73.

Halted ARM64 Port Work (github.com/rcarmo)

3 points

8 days ago

74.

Show HN: Reliability layer to prevent LLM hallucinations (github.com/Upsonic)

3 points

a year ago

75.

Anchor – Zero-dependency LLM hallucination detector (github.com/malaxiya202505https:)

3 points

a day ago

76.

Show HN: 5-translation RAG matrix fixing LLM religious hallucinations (github.com/salaamalykum)

3 points

2 months ago

77.

Show HN: VigIA – A deterministic FSM in .NET 10 to stop LLM hallucinations (github.com/JordanCT)

3 points

2 months ago

78.

LLM Alignment/Hallucinations Can't Be Fixed – Proof (github.com/moketchups)

3 points

4 months ago

79.

We tried injecting hallucinogenics into vision models (github.com/encord-team)

3 points

3 years ago

80.

Show HN: A closed source engine that stops hallucinations deterministically (github.com/007andahalf)

2 points

3 months ago

81.

Show HN: LLMs don't hallucinate because they're bad at math, it's the format (github.com/yvonboulianne)

2 points

2 months ago

82.

Show HN: Hallx – Hallucination risk scoring for LLM outputs (github.com/dhanushk-offl)

2 points

2 months ago

83.

Eliminating hallucination under adversarial conditions 0/30 vs. 6/30, same model (github.com/ediestel)

2 points

eckhart_diestel

2 months ago

84.

Show HN: Phantom Guard – Detect AI-hallucinated package attacks (github.com/matte1782)

2 points

5 months ago

85.

RenderScholar – Scrape real papers from Google Scholar (no hallucinations) (github.com/peterdunson)

2 points

8 months ago

86.

Show HN: AI Chat for Research with References (>10-20 PDFs, No Hallucinations) (wallstr.chat)

2 points

a year ago

87.

Stalwart-Sentinel – A physics-based logic gate to stop AI hallucinations (github.com/taxischramm347-pixel)

2 points

2 months ago

88.

N8n-as-code: Stop n8n AI hallucinations with TS decorators (github.com/EtienneLescot)

2 points

3 months ago

89.

DeepSeek-R1 Is Mathematically Bound to Hallucinate (gist.github.com)

2 points

4 months ago

90.

Show HN: The Calibration game – get better at identifying hallucination in LLMs (calibrationgame.com)

2 points

2 years ago