Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
91.
Hallucinations in your custom AI bot? Clean your data and add sources (github.com/focused-labs)
2 points
re_jem
3 years ago
1 comment
92.
Turing sentence: This program does not halt (github.com/raoofha)
2 points
raoof
5 years ago
1 comment
93.
Catch hallucinated, typosquatted, non-canonical dependencies before production (github.com/brennhill)
2 points
chillax
a month ago
discuss
94.
Show HN: I block LLM hallucinations with a cognitive math framework(re!Think it) (github.com/RealEgor)
2 points
Real_Egor
2 months ago
discuss
95.
QCK-FDP: Hallucination Detection 30,000x Faster. Runs on CPU (github.com/QCK-Framework)
2 points
qck-framework
3 months ago
discuss
96.
Show HN: I wrote a prompt to stop Gemini from hallucinating
2 points
Ginsabo
4 months ago
discuss
97.
Show HN: Serve LLM – Spin up a hallucinated web app from a single prompt (github.com/gerkensm)
2 points
unbehagen
8 months ago
discuss
98.
Rails Lens – Model annotations and ERDs that eliminate AI hallucinations (github.com/seuros)
2 points
averrois
10 months ago
discuss
99.
Show HN: Dingo 1.9.0 released: With enhanced hallucination detection (github.com/MigoXLab)
2 points
e06084
10 months ago
discuss
100.
Show HN: AI Distiller (aid) reduces hallucinations during vibe coding (github.com/janreges)
2 points
jregmail
a year ago
discuss
101.
Think Before You Speak – Exploratory Forced Hallucination Study [pdf] (github.com/AutomationOptimization)
2 points
airylizard
a year ago
discuss
102.
Inducing LLM Hallucinations (github.com/haizelabs)
2 points
leonardtang
2 years ago
discuss
103.
Sphynx: Fuzz Testing Hallucination Detection Models (github.com/haizelabs)
2 points
leonardtang
2 years ago
discuss
104.
Show HN: AI image models hallucinate history, we built a method to fix it it (github.com/Mysticbirdie)
1 point
MysticBirdie
3 months ago
2 comments
105.
Show HN: Vex Runtime reliability layer that auto-corrects AI-Agent hallucination (github.com/vex-hq)
1 point
vex-ai-dev
3 months ago
2 comments
106.
Show HN: Regression tests for detecting cross-domain hallucinations in LLMs
1 point
Ginsabo
4 months ago
2 comments
107.
InsAIts: Monitoring for AI-AI comms. Detect hallucinations before propagation (github.com/Nomadu27)
1 point
MrSteaddy
4 months ago
2 comments
108.
Show HN: A Markdown DSL to stop AI agents from hallucinating UI code (github.com/MegaByteMark)
1 point
MegaByteMark
3 months ago
1 comment
109.
Show HN: I built a graph store so my LLM can't hallucinate facts from my data (github.com/TyKolt)
1 point
TyKolt
3 months ago
1 comment
110.
Show HN: 412 deterministic modules so AI agents stop hallucinating commands (github.com/flytohub)
1 point
ChesterHsu
3 months ago
1 comment
111.
Toroidal Logit Bias – Reduce LLM hallucinations 40% with no fine-tuning (github.com/Paraxiom)
1 point
slye514
4 months ago
1 comment
112.
Show HN: VOR – A verified runtime with 0% hallucination via observations
1 point
CULPRITCHAOS
4 months ago
1 comment
113.
Show HN: CodeGate – An open-source CLI to detect AI-hallucinated packages (github.com/dariomonopoli-dev)
1 point
mondra
6 months ago
1 comment
114.
Show HN: EvalView pytest style tests for AI agents (budgets, hallucinations) (github.com/hidai25)
1 point
hidai25
6 months ago
1 comment
115.
I added native time awareness to CrewAI to fix LLM date hallucinations (github.com/crewAIInc)
1 point
sherwin27
6 months ago
1 comment
116.
Show HN: AgentAudit – open-source hallucination detector for RAG (github.com/jakops88-hub)
1 point
northerndev
6 months ago
1 comment
117.
RenderScholar – Scrape real papers from Google Scholar (no hallucinations) (github.com/peterdunson)
1 point
peterdunson
8 months ago
1 comment
118.
MARM Protocol: Enhancing LLM Memory and Mitigating Hallucinations (github.com/Lyellr88)
1 point
CogniFlow
a year ago
1 comment
119.
Show HN: An adaptive classifier that detects hallucinations in LLM/RAG outputs (github.com/codelion)
1 point
codelion
a year ago
1 comment
120.
Hackers tell Sony to halt the release of the Interview (gist.github.com)
1 point
mwillmott
11 years ago
discuss
More