Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Falcon on Huggingface.co
(huggingface.co)
1 point
pajop
3 years ago
discuss
2.
▲
DeepSeek v4
(api-docs.deepseek.com)
2091 points
impact_sy
a month ago
1607 comments
3.
▲
DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]
(huggingface.co)
982 points
pretext
6 months ago
465 comments
4.
▲
Fine-tune your own Llama 2 to replace GPT-3.5/4
955 points
kcorbitt
3 years ago
181 comments
5.
▲
Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context
(phind.com)
891 points
rushingcreek
3 years ago
347 comments
6.
▲
Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B
(phind.com)
813 points
rushingcreek
3 years ago
284 comments
7.
▲
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
(github.com/cactus-compute)
775 points
HenryNdubuaku
22 days ago
211 comments
8.
▲
Show HN: Tabby – A self-hosted GitHub Copilot
(github.com/TabbyML)
627 points
wsxiaoys
3 years ago
126 comments
9.
▲
Qwen-Image: Crafting with native text rendering
(qwenlm.github.io)
544 points
meetpateltech
10 months ago
159 comments
10.
▲
Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete
(huggingface.co)
534 points
williamzeng0
4 months ago
153 comments
11.
▲
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
(github.com/MinishLab)
442 points
Bibabomas
17 days ago
150 comments
12.
▲
Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview
(github.com/dirac-run)
393 points
GodelNumbering
a month ago
148 comments
13.
▲
Show HN: Natural-SQL-7B, a strong text-to-SQL model
(github.com/cfahlgren1)
362 points
thecalebf
2 years ago
168 comments
14.
▲
Show HN: Qwen-2.5-32B is now the best open source OCR model
(github.com/getomni-ai)
211 points
themanmaran
a year ago
47 comments
15.
▲
Show HN: Improving search ranking with chess Elo scores
(zeroentropy.dev)
193 points
ghita_
a year ago
65 comments
16.
▲
Show HN: Chonky – a neural approach for text semantic chunking
(github.com/mirth)
169 points
hessdalenlight
a year ago
35 comments
17.
▲
Omnilingual ASR: Advancing automatic speech recognition for 1600 languages
(ai.meta.com)
162 points
jean-
7 months ago
45 comments
18.
▲
Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model
153 points
BAAIBeijing
2 years ago
27 comments
19.
▲
Show HN: Benchmarking VLMs vs. Traditional OCR
(getomni.ai)
146 points
themanmaran
a year ago
40 comments
20.
▲
Show HN: ArchGW – An intelligent edge and service proxy for agents
(github.com/katanemo)
118 points
honorable_coder
a year ago
15 comments
21.
▲
Show HN: ART – a new open-source RL framework for training agents
(github.com/OpenPipe)
116 points
kcorbitt
a year ago
12 comments
22.
▲
Launch HN: Flywheel (YC S25) – Waymo for Excavators
103 points
jashmota
8 months ago
78 comments
23.
▲
Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1
(medium.com)
83 points
peakji
2 years ago
19 comments
24.
▲
Show HN: Use functional tokens for AI agents to simplify app workflows
(nexa4ai.com)
80 points
alanzhuly
2 years ago
10 comments
25.
▲
Show HN: Hyperparam: OSS tools for exploring datasets locally in the browser
(hyperparam.app)
77 points
platypii
a year ago
21 comments
26.
▲
Show HN: Arch-Router – 1.5B model for LLM routing by preferences, not benchmarks
66 points
adilhafeez
a year ago
15 comments
27.
▲
Show HN: Open-source model and scorecard for measuring hallucinations in LLMs
(vectara.com)
65 points
eskibars
3 years ago
14 comments
28.
▲
Show HN: Using LLMs and Embeddings to classify application errors
(github.com/highlight)
65 points
vadman97
3 years ago
10 comments
29.
▲
Show HN: Lance – image/video generation and understanding in one model
(github.com/bytedance)
62 points
cleardusk
14 days ago
15 comments
30.
▲
Show HN: OCR Benchmark Focusing on Automation
(nanonets.com)
58 points
prats226
a year ago
21 comments
More