codelion
Automating eval design and hillclimbing with Claude
DataInventor – an open-source replication of Adaption Lab's Invent a Dataset
Typed Decisions: an open benchmark for decision models (official on HF)
Show HN: MeraGEO – check whether ChatGPT, Claude and Gemini name your brand
Re:Gemini 4 Argon
on Wednesday September 30, 2026 @11:23PM (#49917349)
Is it available for public yet or just selected companies?
Neural Drive
Cross-Lingual Alignment Without Joint Training
Voice AI Benchmarks: a directory of voice-agent evaluations
Neural Canvas: a fruit fly connectome demo in the browser
Iris: Climbing to the Search Frontier
The Recursive Economy: AI Self-Improvement and Scarcity
Re:Writing fingerprint analysis of responses reveals Kimi's similarity...
on Thursday July 23, 2026 @11:31AM (#49023216)
How do you do cross entropy analysis for Claude without logits?
Re:Annoying and alarming things about OpenCode
on Wednesday July 22, 2026 @11:44PM (#49016671)
Another reason to avoid it at all costs if you needed it - https://x.com/thdxr/status/2079623963995467869?s=20
Re:Annoying and alarming things about OpenCode
on Monday July 20, 2026 @09:30AM (#48978644)
Finally good seeing someone else also getting frustrated with OpenCode and posting the issues.
Neural Drive, a SuperTuxKart World Model that runs in the browser
Coding agent for local models on a Mac
Re:Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help?
on Saturday July 18, 2026 @11:13AM (#48958865)
Just use OpenEvolve for such problems.
Re:Reviving a 15-year-old netbook with Arch Linux
on Saturday July 18, 2026 @02:02AM (#48955610)
I use a 2010 Macbook Air with Linux XFCE desktop and it works well for browsing and simple office work.
Frame: Grounding LLM Vulnerability Detection with a Sound Separation-Logic Core
Re:Ask HN: Has anyone replaced Claude/GPT with a local model for daily...
on Monday June 15, 2026 @09:47PM (#48549542)
Using qwen3.6 27b locally with Claude code, it works well for simple coding tasks
Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon
A 1B humanizer that matches human writing on an AI detector
Re:Velonus – Open-source AppSec scanner that deduplicates SAST noise
on Friday May 15, 2026 @12:35AM (#48144601)
You can consider using Frame for the SAST part - https://github.com/lambdasec/frame
Re:Ollama is now powered by MLX on Apple Silicon in preview
on Tuesday March 31, 2026 @12:50AM (#47582875)
How does it compare to some of the newer mlx inference engines like optiq that support turboquantization - https://mlx-optiq.pages.dev/
Zero-Dependency Programming
Re:US Court of Appeals: TOS may be updated by email, use can imply con...
on Monday March 09, 2026 @03:53AM (#47305987)
the key issue is the interpretation of "consent" when continued use is the only option. aree users truly consenting, or are they simply left with no alternative?