HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
241.
▲
Show HN: Self-hostable academic paper manager (linxiv)
github.com/linxiv-dev
discuss
3 days ago
jeuribe
3 points
242.
▲
Show HN: Signals – finding the most informative agent traces without LLM judges
arxiv.org
discuss
3 months ago
sparacha
3 points
243.
▲
Diffusion LLM may make most of the AI engineering stack obsolete
discuss
3 months ago
victorpiles99
3 points
244.
▲
Native Parallel Reasoner: Self-Evolving to Learn Parallel Reasoning
discuss
6 months ago
jacklanda
3 points
245.
▲
Show HN: Construct – API-first coding assistant with CodeAct tool calling
github.com/Furisto
discuss
6 months ago
furisto
3 points
246.
▲
Show HN: Praval Agentic AI Framework
github.com/aiexplorations
discuss
7 months ago
aiexplorations
3 points
247.
▲
Show HN: Inworld TTS open sourcing and technical report
github.com/inworld-ai
discuss
a year ago
feifan123
3 points
248.
▲
Show HN: MLE-Agent – A lightweight AI agent to help you win Kaggle
github.com/MLSysOps
discuss
2 years ago
Hunter_Zhang_
3 points
249.
▲
RES-Q: A New Benchmark for Differentiating Frontier Model Capability
discuss
2 years ago
becklabs
3 points
250.
▲
Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model
discuss
3 years ago
BAAIBeijing
3 points
251.
▲
Show HN: RETVec: Resilient and Efficient Text Vectorizer
discuss
3 years ago
ebursztein
3 points
252.
▲
Show HN: Multimodal Maestro – Prompt tools for use with LMMs
github.com/roboflow
discuss
3 years ago
zerojames
3 points
253.
▲
Show HN: AWS Pricing Add-On for Google Sheets
workspace.google.com
discuss
3 years ago
ary
3 points
254.
▲
Show HN: How simple (but clever) algorithms can find label issues in datasets
playground.cleanlab.ai
discuss
4 years ago
calebchiam
3 points
255.
▲
The most comprehensive benchmark datasets for federated learning to date
discuss
5 years ago
xfzhu
3 points
256.
▲
Show HN: Objective-Reinforced GANs
discuss
9 years ago
gablg1
3 points
257.
▲
Show HN: Paper Lantern – improving Autoresearch with research knowledge
paperlantern.ai
2 comments
2 months ago
paperlantern
2 points
258.
▲
Show HN: SkillFortify, Formal verification for AI agents (auto-discovers)
github.com/varun369
1 comment
4 months ago
varunpratap369
2 points
259.
▲
Show HN: Samma Suit – Open-source 8-layer security framework for AI agents
sammasuit.com
1 comment
4 months ago
jbwagoner
2 points
260.
▲
Show HN: EchoMode – A stability layer that prevents persona drift in LLMs
github.com/Seanhong0818
1 comment
8 months ago
teamechomode
2 points
261.
▲
Show HN: Helices Create a New Model of Deterministic Computation [pdf]
lambdalord.github.io
1 comment
a year ago
bkaminsky
2 points
262.
▲
Show HN: Portaltext, grand strategy-style recursive tooltips for the web
portaltext.com
discuss
7 days ago
alaskahoffman
2 points
263.
▲
Show HN: Glq LLM quantization using E8 lattice
github.com/cnygaard
discuss
22 days ago
acd
2 points
264.
▲
Show HN: LLM-Rosetta - Translate LLM API Calls Across OpenAI, Anthropic, Gemini
github.com/Oaklight
discuss
2 months ago
Oaklight
2 points
265.
▲
Show HN: Monogate – EML operator family, hybrid framework, 108-node sin(x)
monogate.dev
discuss
2 months ago
zonked45
2 points
266.
▲
Show HN: AI-nexus – Only 2-3 rules and skills load per prompt in Claude Code
github.com/JSK9999
discuss
3 months ago
suntrix3
2 points
267.
▲
Show HN: GovernsAI – unified auth, memory, and PII guard across AI providers
governsai.com
discuss
4 months ago
shaivpidadi
2 points
268.
▲
Show HN: Edictum – Runtime governance for LLM agent tool calls
discuss
4 months ago
acartag7
2 points
269.
▲
Show HN: Dress – A parameter-free O(E) graph equation that provably exceeds 1-WL
github.com/velicast
discuss
4 months ago
velicast
2 points
270.
▲
Show HN: Formally Verified a Millennium Prize Problem in Coq Yang-Mills Mass Gap
github.com/Shariq81
discuss
4 months ago
shariq81
2 points
More