Viveka: filter LLM output against a Lean-verified Advaita Vedanta model

What it does

pip install " witness-layer[scherf] " The project is called Viveka ; the PyPI package is witness-layer . The [scherf] extra adds the Lean-verified backend — strongly recommended. Viveka (Sanskrit viveka ) — discernment, the capacity to discriminate the real from the unreal. Use Viveka when you need an LLM response filter that checks claims against a formal, machine-verified witness-centered model — catching language that treats the user as an object to be profiled or steered, over-claims epistemic certainty, or induces dependency. LLM output: "Deep down you're just your preference profile." Viveka: Action.CORRECT Axiom A13/M6/M7 (adhyāsa) — verified=True Reframe: "State this conventionally:…from github.com

• 
  Tiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205

  Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM - jmaczan/tiny-vllm

• 
  Open-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65

  Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…

• 
  A new benchmark for testing LLMs for deterministic outputsApr 2026 · interfaze.ai · ▲60

  When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries. The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not. Structured output today is a big part of using LLMs, especially when building deterministic workflows. Current structured output benchmarks (e.g., JSONSchemaBench) only validate…

• 
  Structural Verification for LLMs: Why Best-of-N Isn't EnoughDec 2025 · github.com · ▲5

  A lightweight, no-retraining verification layer that rejects smooth hallucinations by measuring structural tension instead of probability.

• 
  Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)Aug 2026 · github.com · ▲21

  Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining

• 
  Goku – WASM (wllama)-powered LLM inference and model managerJul 2026 · userfrom1995.github.io · ▲9

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 19d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Fundraisly▲1,537

  AI fundraising agent that finds investors and books meetings

  AI · Jun 2026 · fundraisly.com

• 
  Homebrew 6.0.0▲1,481

  Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!

  Dev tools · Jun 2026 · brew.sh

• 
  Performative-UI – A react component library of design tropes▲1,181

  Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!

  Life & fun · Jun 2026 · vorpus.github.io

• 
  Upstream▲976

  The inbox designed for humans and agents

  AI · Jun 2026 · upstream.do

• 
  Goldfish▲958

  Press Option. It knows your work and replies like you

  AI · Jun 2026 · goldfish.sh

• 
  I made Google Trends for Hacker News by indexing 18 years of comments▲822

  Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.

  Life & fun · Jun 2026 · hackernewstrends.com