HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
241.
▲
Show HN: Edictum – Runtime governance for LLM agent tool calls
discuss
4 months ago
acartag7
2 points
242.
▲
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
243.
▲
Show HN: Formally Verified a Millennium Prize Problem in Coq Yang-Mills Mass Gap
github.com/Shariq81
discuss
4 months ago
shariq81
2 points
244.
▲
Show HN: Thoth – Obsidian AI Research Assistant
github.com/acertainKnight
discuss
4 months ago
acertainKnight
2 points
245.
▲
Show HN: Measuring how AI agent teams improve issue resolution on SWE-Verified
arxiv.org
discuss
5 months ago
NBenkovich
2 points
246.
▲
Show HN: Sorting a billion of integers in 7.6 seconds
github.com/egorsmkv
discuss
6 months ago
yehors
2 points
247.
▲
Show HN: Efpix – A flood protocol with E2EE and metadata protection
arxiv.org
discuss
6 months ago
shinymonitor
2 points
248.
▲
Show HN: Model-literals, model-aliases, and preference-aligned routing for LLMs
docs.archgw.com
discuss
9 months ago
honorable_coder
2 points
249.
▲
Show HN: RouteGPT – model routing on ChatGPT aligned to user preferences
chromewebstore.google.com
discuss
a year ago
honorable_coder
2 points
250.
▲
Show HN: Communal Growth, find others with similar interests in books or papers
communalgrowth.org
discuss
a year ago
CarpaDorada
2 points
251.
▲
Show HN: LLM-Bible – A Visual Interface for Exploring the Latest LLM Research
llm-bible.github.io
discuss
a year ago
sjm213
2 points
252.
▲
Show HN: DataBridge: Open-Source Multi-Modal Parser and Retriever for LLMs
github.com/databridge-org
discuss
a year ago
Adityav369
2 points
253.
▲
Cot Decoding – Eliciting Reasoning from LLMs
discuss
2 years ago
codelion
2 points
254.
▲
Show HN: I reproduced Code Llama fill-in-the-middle code completion training
github.com/BohdanPetryshyn
discuss
2 years ago
BohdanPetryshyn
2 points
255.
▲
Show HN: Can AI keep my code up-to-date?
github.com/xeol-io
discuss
2 years ago
shihanwan1
2 points
256.
▲
Tree of Thoughts: Official vs. Wrong Implementation
discuss
3 years ago
ysymyth
2 points
257.
▲
Ask HN: What is your take on carbon emissions of Machine Learning
discuss
4 years ago
danschmitt
2 points
258.
▲
ICRA2020: Unsupervised Depth Completion from Visual Inertial Odometry
discuss
5 years ago
alexklwong
2 points
259.
▲
Neuzz: A neural-network-assisted fuzzer(S&P 19)
discuss
7 years ago
Dongdongshe
2 points
260.
▲
Ask HN: Convolutional VS Recurrent/LSTM/GRU neural networks
discuss
8 years ago
ghosthamlet
2 points
261.
▲
A simple Jpeg defense for the attack from OpenAI authors
discuss
9 years ago
VinayUPrabhu
2 points
262.
▲
Show HN: Unstable Singularity Detector update 1.4.1
github.com/Flamehaven
2 comments
8 months ago
Flamehaven
1 points
263.
▲
EvidionAI – open-source multi-agent research system built on LangGraph
1 comment
3 months ago
NeuralOperator
1 points
264.
▲
Show HN: Private AI Document Server
github.com/queryhat
1 comment
4 months ago
chhetri978
1 points
265.
▲
Show HN: Klaus – a Claude Code native delegating agentic harness
1 comment
5 months ago
blas0
1 points
266.
▲
Ask HN: Licensing for Research Papers
1 comment
3 years ago
pksebben
1 points
267.
▲
Show HN: VQAScore – open eval metric/reward model, now for text-to-video
github.com/linzhiqiu
discuss
15 days ago
linzhiqiu
1 points
268.
▲
Show HN: Self-hosted Spanner-like database that speaks Redis
github.com/swytchdb
discuss
a month ago
withinboredom
1 points
269.
▲
Ask HN: At ~165k tokens, does Opus 4.6 1M outperform Opus 4.6 200k?
discuss
2 months ago
consumer451
1 points
270.
▲
Show HN: Karpathy's Autoresearch with Evolutionary Database
github.com/hgarud
discuss
3 months ago
hgarud
1 points
More