Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
241.
▲
Show HN: 100% LLM accuracy–no fine-tuning, JSON only
(github.com/Mysticbirdie)
2 points
MysticBirdie
3 months ago
2 comments
242.
▲
Show HN: Alignmenter – Measure brand voice and consistency across model versions
(alignmenter.com)
2 points
justingrosvenor
7 months ago
2 comments
243.
▲
Show HN: I built a linter for undocumented linter warnings. AI hates me now
(github.com/BKDDFS)
2 points
BKDDFS
18 days ago
1 comment
244.
▲
Show HN: Reduce LLM token use by ~30% with this MCP/CLI tool(Claude benchmarked)
2 points
jahala
3 months ago
1 comment
245.
▲
The tech stack I've been refining for 6 years
2 points
creativedg
4 months ago
1 comment
246.
▲
Show HN: OS Library for Conditional Gaussian Mixture Modelling in Python
2 points
sitmo
8 months ago
1 comment
247.
▲
Open Source Library to Perform Entity Embeddings Using Neural Networks
2 points
rodrigobresan
7 years ago
1 comment
248.
▲
Lib of Machine Learning algorithms for Golang
(godoc.org)
2 points
AVidales
12 years ago
discuss
249.
▲
Show HN: TrainForgeTester – deterministic scenario tests for AI agents
(github.com/TrainForge)
2 points
alcray
a month ago
discuss
250.
▲
Show HN: Monogate – EML operator family, hybrid framework, 108-node sin(x)
(monogate.dev)
2 points
zonked45
2 months ago
discuss
251.
▲
TDD Makes a Lot of Sense with Agentic Development
2 points
shellerik
2 months ago
discuss
252.
▲
Show HN: AlphaEvolve inspired evolution harness for Pokemon
(github.com/papercomputeco)
2 points
brianllamar
3 months ago
discuss
253.
▲
Show HN: Automate Claude in a work->review loop with cook
(github.com/rjcorwin)
2 points
staticvar
3 months ago
discuss
254.
▲
Show HN: Reconlify – local-first reconciliation CLI for CSV/TSV and text logs
(github.com/testuteab)
2 points
testuteab
3 months ago
discuss
255.
▲
Show HN: BreakMyAgent – Open-source red-teaming sandbox for LLM system prompts
2 points
breakmyagent
3 months ago
discuss
256.
▲
Ask HN: Why does single-node DDP sometimes get slower with more GPUs?
2 points
traceopt-ai
4 months ago
discuss
257.
▲
Show HN: A Kubernetes Operator to Validate Jupyter Notebooks in MLOps
(github.com/tosin2013)
2 points
takinosh
4 months ago
discuss
258.
▲
Show HN: Sandy – Accelerate AI agents: think once, replay forever
(github.com/Sangkwun)
2 points
sangkwun
4 months ago
discuss
259.
▲
Show HN: Instagram: Private Posts Exposed to Unauthenticated Requests
(github.com/jatin-dot-py)
2 points
jatin-dot-py
4 months ago
discuss
260.
▲
Show HN: Consensus for Side Effects
(github.com/abokhalill)
2 points
yousef06
4 months ago
discuss
261.
▲
Show HN: ProofLoop – Autonomous long-running agents with verifiable completion
(github.com/exiw-ai)
2 points
egordev
5 months ago
discuss
262.
▲
Show HN: Importguard – Measure and enforce Python import-time behavior in CI
(github.com/AryanKumar1401)
2 points
AryanKumar1401
5 months ago
discuss
263.
▲
Show HN: I built a deterministic vector DB kernel in Rust using fixed-point math
(github.com/varshith-Git)
2 points
varshith17
6 months ago
discuss
264.
▲
Show HN: RIMC – An Alpha-Drift Framework for Finite-Speed Learning Markets
(github.com/rimc-lab)
2 points
sode_rimc
6 months ago
discuss
265.
▲
Show HN: prompttest – pytest for LLMs
(github.com/decodingchris)
2 points
decodingchris
9 months ago
discuss
266.
▲
Show HN: Open-source Go repo comparing DCA vs. Grid with reproducible backtests
(github.com/Zmey56)
2 points
Zmey56
9 months ago
discuss
267.
▲
Show HN: PromptProof – CI gate for LLM outputs (schema/regex/cost; no API keys)
(news.ycombinator.com)
2 points
geminimir
9 months ago
discuss
268.
▲
Show HN: Framework to structure LLM dev workflows with Markdown-based protocol
(github.com/Fr-e-d)
2 points
Fr-e-d
10 months ago
discuss
269.
▲
Show HN: Biski64 – Fast PRNG (~.40ns/call), Passes BigCrush/PractRand, Injective
(github.com/danielcota)
2 points
daniel_cota
a year ago
discuss
270.
▲
Show HN: VibeShift MCP – Getting secure working code from AI
(github.com/GroundNG)
2 points
Ilikepizza2
a year ago
discuss
More