HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
211.
▲
Show HN: Open-source model and scorecard for measuring hallucinations in LLMs
vectara.com
14 comments
3 years ago
eskibars
65 points
212.
▲
Show HN: Using LLMs and Embeddings to classify application errors
github.com/highlight
10 comments
3 years ago
vadman97
65 points
213.
▲
Show HN: Aiopandas – Async .apply() and .map() for Pandas, Faster API/LLMs Calls
github.com/telekinesis-inc
16 comments
a year ago
eneuman
62 points
214.
▲
Show HN: Anki-LLM – Bulk process and generate Anki flashcards with LLMs
github.com/raine
23 comments
8 months ago
rane
60 points
215.
▲
Show HN: IncarnaMind-Chat with your multiple docs using LLMs
github.com/junruxiong
28 comments
3 years ago
joeyxiong
57 points
216.
▲
Show HN: LLMWare – Small Specialized Function Calling 1B LLMs for Multi-Step RAG
github.com/llmware-ai
6 comments
2 years ago
doberst0103
51 points
217.
▲
tinymcp: Let LLMs control embedded devices via the Model Context Protocol
github.com/golioth
10 comments
a year ago
hasheddan
49 points
218.
▲
Show HN: TensorZero – open-source data and learning flywheel for LLMs
github.com/tensorzero
2 comments
2 years ago
GabrielBianconi
49 points
219.
▲
Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience
13 comments
a year ago
codelion
48 points
220.
▲
Show HN: Data Bonsai: a Python package to clean your data with LLMs
github.com/databonsai
6 comments
2 years ago
alvin_r_h
47 points
221.
▲
Show HN: Epstein's emails reconstructed in a message-style UI (OCR and LLMs)
github.com/Toon-nooT
8 comments
6 months ago
toon-noot
46 points
222.
▲
Show HN: LLM, a Rust Crate/CLI for CPU Inference of LLMs (LLaMA, GPT-NeoX, etc.)
github.com/rustformers
4 comments
3 years ago
Philpax
45 points
223.
▲
Are LLMs able to play the card game Set?
github.com/vnglst
31 comments
a year ago
vnglst
43 points
224.
▲
llamafile: Distribute and Run LLMs with a Single File
github.com/mozilla-ai
7 comments
6 months ago
stefankuehnel
43 points
225.
▲
Show HN: Solving the ~95% legislative coverage gap using LLM's
lustra.news
23 comments
6 months ago
fokdelafons
41 points
226.
▲
Show HN: Gerbil – an open source desktop app for running LLMs locally
github.com/lone-cloud
12 comments
7 months ago
lone-cloud
37 points
227.
▲
Show HN: I just open sourced my document/website extractor for Vision-LLMs
github.com/emcf
4 comments
2 years ago
emmettm
37 points
228.
▲
Show HN: Watch LLMs play 21,000 hands of Poker
pokerbench.adfontes.io
19 comments
5 months ago
jazarwil
36 points
229.
▲
Show HN: Waiting for LLMs Suck – Give your user a game
github.com/ftaip
18 comments
2 months ago
dalemhurley
36 points
230.
▲
Local File Organizer: Organize your files using multi-modal LLMs
github.com/QiuYannnn
5 comments
2 years ago
oidar
36 points
231.
▲
Stop Evaluating LLMs on Vibes
github.com/truera
7 comments
3 years ago
shayaks
35 points
232.
▲
Show HN: Use LLMs to Interact with APIs
github.com/FlowTestAI
5 comments
2 years ago
jsajal1993
35 points
233.
▲
vLLM-MLX – Run LLMs on Mac at 464 tok/s
github.com/waybarrios
3 comments
5 months ago
waybarrios
33 points
234.
▲
Show HN: Helium – a headless, open-source LMS
github.com/thoughtindustries
14 comments
3 years ago
ricotico060
31 points
235.
▲
Show HN: Mutahunter – LLMs to support mutating testing for all major languages
github.com/codeintegrity-ai
9 comments
2 years ago
coderinsan
31 points
236.
▲
Clojure → YAMLScript transpiler: using LLMs for normalization, SCI for execution
github.com/whitecell-dev
discuss
a month ago
MaykonMan
31 points
237.
▲
Show HN: The Analog I – Inducing Recursive Self-Modeling in LLMs [pdf]
github.com/philMarcus
43 comments
5 months ago
Phil_BoaM
29 points
238.
▲
Show HN: a Rust lib to trigger actions based on your screen activity (with LLMs)
github.com/louis030195
13 comments
2 years ago
m-louis030195
29 points
239.
▲
Show HN: 1v1 coding game that LLMs struggle with
yare.io
8 comments
4 months ago
levmiseri
29 points
240.
▲
Show HN: LLM-docs, software documentation intended for consumption by LLMs
github.com/Dicklesworthstone
7 comments
a year ago
eigenvalue
28 points
More