Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
31.
Show HN: PyBroker – Algotrading in Python with Machine Learning (github.com/edtechre)
70 points
pyfreak182
3 years ago
15 comments
32.
Show HN: Arch-Router – 1.5B model for LLM routing by preferences, not benchmarks
66 points
adilhafeez
a year ago
15 comments
33.
Show HN: Marqo – Vectorless Vector Search (github.com/marqo-ai)
62 points
jn2clark
3 years ago
15 comments
34.
Show HN: Entropy-Guided Loop – How to make small models reason (github.com/monostate)
33 points
andrewmonostate
9 months ago
4 comments
35.
Show HN: Bhatti – Self-hostable Firecracker orchestrator with auto pause/wake (bhatti.sh)
19 points
sahil-shubham
a month ago
4 comments
36.
Suggest HN: Please keep hnsearch.com up (shutting tomorrow)
10 points
cjbarber
12 years ago
2 comments
37.
Show HN: MinimalChat – A Simple and Customizable LLM Chat Application (github.com/fingerthief)
6 points
fingerthieff
2 years ago
discuss
38.
Show HN: Smart glasses that tell me when to stop pouring (github.com/RealComputer)
5 points
tash_2s
3 months ago
7 comments
39.
Show HN: Adaptive-classifier – text classification with continuous learning
5 points
codelion
a year ago
1 comment
40.
Show HN: Structural Verification for LLMs: Why Best-of-N Isn't Enough (github.com/ShinobuMiya)
5 points
shinobu_miya
6 months ago
discuss
41.
Show HN: Project Chimera – Hybrid AI Agent Combining LLM, Symbolic, and Causal (github.com/akarlaraytu)
4 points
aytuakarlar
9 months ago
3 comments
42.
Ask HN: Do we need 100B+ parameters in a large language model?
4 points
sourabh03agr
3 years ago
1 comment
43.
Show HN: Kubernetes Security Profile Generator Using eBPF
4 points
mrayas
3 months ago
discuss
44.
Show HN: DeepShot – NBA Game Predictor with 70% Accuracy Using EWMA and XGBoost (github.com/saccofrancesco)
4 points
s4ccofrancesco
5 months ago
discuss
45.
Show HN: 1.5B LLM routing model that aligns to preferences, not leaderboards (huggingface.co)
4 points
honorable_coder
a year ago
discuss
46.
Ask HN: Suggesting better employee-supporting AI Chatbot to a mid sized corpo
3 points
ouraf
3 years ago
5 comments
47.
Show HN: Alexplainable: Early prototype of a transparent image recognizer (github.com/joy-void-joy)
3 points
joy_void_joy
2 years ago
discuss
48.
Show HN: AI-runtime-guard – Policy enforcement layer for MCP AI agents (github.com/jimmyracheta)
2 points
JimmyRacheta
3 months ago
2 comments
49.
Show HN: Local memory layer for AI agents, survives restarts, no embeddings (screenapp.io)
2 points
JosephjackJR
3 months ago
discuss
50.
Show HN: Sigma Runtime – model-agnostic identity control for LLMs (github.com/sigmastratum)
2 points
teugent
5 months ago
discuss
51.
Show HN: Stability First AI – Recovering memory without training data (github.com/vitali-sialedchyk)
2 points
StabilityFirst
5 months ago
discuss
52.
Show HN: Romforth Ported to the IBM 1130 (github.com/romforth)
2 points
romforth
6 months ago
discuss
53.
GPT-4 leaks its own API internals through training data exposure
1 point
safteylayer
3 months ago
5 comments
54.
Show HN: Market Digest: Self-hosted market analysis and Telegram (github.com/mutaaf)
1 point
mutaaf
3 months ago
2 comments
55.
Show HN: Pure Go mosh client, server, and WASM build for the browser (github.com/unixshells)
1 point
rasengan
2 months ago
1 comment
56.
Show HN: AI personas in executable .aix files (run like containers) (github.com/mjtiv)
1 point
BlackWater85
10 months ago
1 comment
57.
Show HN: Safely rename files to their SHA1 sum + ext on FreeBSD 11
1 point
eriknstr
10 years ago
1 comment
58.
Show HN: Wiredigg – Real-Time Network Analysis with ML and Ollama Support
1 point
justvugg
3 months ago
discuss
59.
Show HN: Membrane, revisable memory for long lived AI agents (github.com/GustyCube)
1 point
GustyCube
4 months ago
discuss
60.
Show HN: 500-cycle runtime test for long-horizon LLM coherence (zenodo.org)
1 point
teugent
4 months ago
discuss
More