HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
241.
▲
Show HN: Reconlify – local-first reconciliation CLI for CSV/TSV and text logs
github.com/testuteab
discuss
4 months ago
testuteab
2 points
242.
▲
Show HN: BreakMyAgent – Open-source red-teaming sandbox for LLM system prompts
discuss
4 months ago
breakmyagent
2 points
243.
▲
Ask HN: Why does single-node DDP sometimes get slower with more GPUs?
discuss
4 months ago
traceopt-ai
2 points
244.
▲
Show HN: A Kubernetes Operator to Validate Jupyter Notebooks in MLOps
github.com/tosin2013
discuss
5 months ago
takinosh
2 points
245.
▲
Show HN: Sandy – Accelerate AI agents: think once, replay forever
github.com/Sangkwun
discuss
5 months ago
sangkwun
2 points
246.
▲
Show HN: Instagram: Private Posts Exposed to Unauthenticated Requests
github.com/jatin-dot-py
discuss
5 months ago
jatin-dot-py
2 points
247.
▲
Show HN: ProofLoop – Autonomous long-running agents with verifiable completion
github.com/exiw-ai
discuss
5 months ago
egordev
2 points
248.
▲
Show HN: Importguard – Measure and enforce Python import-time behavior in CI
github.com/AryanKumar1401
discuss
6 months ago
AryanKumar1401
2 points
249.
▲
Show HN: RIMC – An Alpha-Drift Framework for Finite-Speed Learning Markets
github.com/rimc-lab
discuss
7 months ago
sode_rimc
2 points
250.
▲
Show HN: prompttest – pytest for LLMs
github.com/decodingchris
discuss
10 months ago
decodingchris
2 points
251.
▲
Show HN: PromptProof – CI gate for LLM outputs (schema/regex/cost; no API keys)
news.ycombinator.com
discuss
10 months ago
geminimir
2 points
252.
▲
Show HN: Framework to structure LLM dev workflows with Markdown-based protocol
github.com/Fr-e-d
discuss
a year ago
Fr-e-d
2 points
253.
▲
Show HN: VibeShift MCP – Getting secure working code from AI
github.com/GroundNG
discuss
a year ago
Ilikepizza2
2 points
254.
▲
Show HN: Open-Source Conversational Analytics
github.com/Channel-Labs
discuss
a year ago
otterk10
2 points
255.
▲
Show HN: NODEFit – Fit Time-Series with Neural Differential Equations
github.com/gpavanb1
discuss
2 years ago
gpavanb
2 points
256.
▲
Show HN: Play Euchre with AI Bots
euchre.fewworddotrick.com
discuss
3 years ago
swpecht
2 points
257.
▲
Show HN: CLI for testing and evaluating LLM prompts and outputs
github.com/promptfoo
discuss
3 years ago
typpo
2 points
258.
▲
My Favorite Off-the-Shelf Data Science Repos, What Are Yours?
discuss
4 years ago
floriankuwala
2 points
259.
▲
pDoS – censorship resistant collaborative DDoS-ing
discuss
7 years ago
sexyboy9
2 points
260.
▲
Tell HN: Google sells Gemini Code Assist, but their back end bans paying users
2 comments
3 months ago
tmdazrafa
1 points
261.
▲
Show HN: System that rediscovers physics laws from raw data autonomously
protoscience.ai
2 comments
3 months ago
strujillo
1 points
262.
▲
Show HN: EV range calculator – range circles and charger map (700 models)
2 comments
4 months ago
sthorat
1 points
263.
▲
Show HN: 2048 with Blitz Mode
bobbby.online
1 comment
a month ago
rhgraysonii
1 points
264.
▲
Ask HN: CVAT users, how do you QA labels?
1 comment
5 months ago
Abderrahman54
1 points
265.
▲
Show HN: Lib0xc, the C standard library you wish you had
github.com/microsoft
discuss
2 months ago
EPWN3D
1 points
266.
▲
Show HN: RepoGauge – save token costs and compare agents on your own repos
repogauge.org
discuss
2 months ago
siliconc0w
1 points
267.
▲
Show HN: Skilldeck – Desktop app to manage AI agent skill files across tools
github.com/ali-erfan-dev
discuss
2 months ago
alierfan
1 points
268.
▲
Show HN: A technique for self-improving agents
discuss
3 months ago
dataviz1000
1 points
269.
▲
Show HN: Caelix, a balanced-ternary lattice field laboratory
caelix.co.uk
discuss
3 months ago
alan_caelix
1 points
270.
▲
Show HN: Evalcraft – cassette-based testing for AI agents (pytest, $0/run)
github.com/beyhangl
discuss
4 months ago
beyhang
1 points
More