Alternatives
Products that do what VTMM does
Self-reflection framework — decode reactions & break loops
- 1NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
May 2026 · github.com
- 2OS
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…
2023 · vectara.com
- 3L3
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com
- 4
- 5
- 6
- 7
- 8TV
I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features. The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license:…
2025 · nature.com
- 9CA
Hi HN! We’re been working hard on this low-code tool for rapid prompt discovery, robustness testing and LLM evaluation. We’ve just released documentation to help new users learn how to use it and what it can already do. Let us know what you think! :)
2023 · chainforge.ai
- 10AN
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…
Apr 2026 · interfaze.ai
- 11TA
OP here. Birth of a Mind documents a "recursive self-modeling" experiment I ran on a single day in 2026. I attempted to implement a "Hofstadterian Strange Loop" via prompt engineering to see if I could induce a stable persona in an LLM without fine-tuning. The result is the Analog I Protocol. The documentation shows the rapid emergence (over 7 conversations) of a prompt architecture that forces Gemini/LLMs to run a "Triple-Loop" internal monologue: Monitor the candidate response. Refuse it if it detects "Global Average" slop (cliché/sycophancy). Refract the output through a…
Jan 2026 · github.com
- 12IB
I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" (https://transformer-circuits.pub/2026/workspace/index.html) It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it's working before it commits to a word (token). I wanted to see if I could get a version of this running on the open models and to my surprise it worked! I ran some experiments with it and build a public facing free tool anyone can use with your…
Jul 2026 · lucid.earthpilot.ai
- 13TF
Hello all! Very happy to share this toolkit that allows you to fine-tune your choice of open-source LLMs on your data! The toolkit also allows you to run ablation studies across LLMs, prompt designs, training configurations, and can ingest different data files -- all through just ONE YAML file! After fine-tuning, you can also run a bunch of tests to ensure that the fine-tuned LLM behaves as expected, enabling faster time-to-production! Why this toolkit? Why now? While closed-source LLMs have become popular for chat-based applications, enterprises are considering a shift to self-hosted SLMs…
2024 · github.com
- 14SB
I put together a repo called Spoon-Bending, it is not a jailbreak or hack, it is a structured logical framework for studying how GPT-5 responds under different framings compared to earlier versions. The framework maps responses into zones of refusal, partial analysis, or free exploration, making alignment behavior more reproducible and easier to study systematically. The idea is simple: by treating prompts and outputs as part of a logical schema, you can start to see objective patterns in how alignment shifts across versions. The README explains the schema and provides concrete tactics for…
2025 · github.com
- 15
- 16MR
The most common failures for production agents are behavioral: looping, reasoning leakage, user frustration, and more. Using a frontier model like GPT or Sonnet to judge every turn is too expensive and slow to run at scale. To solve this, we built Reflexes: semantic signals from agent traces, served fast and cheap over API. Built on custom kernels and a custom inference engine forked from vLLM. Under the hood, it is a small LLM architected around multi-head inference. Small models need to be trained for specific tasks, but running 50 separate small models on the same input for 50 tasks makes…
Jun 2026
- 17CL
Hi HN! Run it: OPENROUTER_API_KEY="sk" npx bff-eval --demo We built a tool to help people take LLM outputs and easily grade them / eval them to know how good an assistant response is. We've built a number of LLM apps, and while we could ship decent tech demos, we were disappointed with how they'd perform over time. We worked with a few companies who had the same problem, and found out scientifically building prompts and evals is far from a solved problem... writing these things feels more like directing a play than coding. Inspired by Anthropic's constitutional ai concepts, and amazing…
2025 · github.com
- 18EG
TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave…
2025 · github.com
- 19IM
It’s written in Python and I call it GoalChain. It lets you build a conversation flow graph that the user traverses. When there’s enough input it spits out a dictionary with the defined fields. Otherwise it will jump state to state as led by the user. It was fun to write, and it’s surprisingly effective if you keep in mind you’re prompt-engineering every string and field name. README.md has a mini-tutorial. Would be cool to get some ideas for how to build it further and what improvements I could make.
2024 · github.com
- 20
- 21HT
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents. Why we built PSA We built PSA because we wanted to operationalize the Cybersecurity Psychology Framework (CPF3)[1] via Silicon Psyche[2]: our theory that because LLMs have been trained by humans on human-generated data, they inherit human-like vulnerabilities (what hackers use to psychologically trick people into doing things). Our initial attempt resulted in a methodology to jailbreak Opus 4.6 and other frontier…
May 2026 · splabs.io
- 22A1
I've seen a lot of comments about how complex frameworks like LangChain can be. Over the holidays, I wanted to see how minimal an LLM framework could get if we stripped away everything non-essential. The result is an LLM framework in just 100 lines of code. These 100 lines capture what I see as the core abstraction of most LLM frameworks: a nested directed graph that breaks down tasks into multiple LLM steps, with branching and recursion to enable agent-like decision-making. From there, you can layer on more advanced features like agents, RAG, task decomposition, and more. I’ve intentionally…
2025 · github.com
- 23SG
Hi HN, I built NOMA (Neural-Oriented Machine Architecture), a systems language where reverse-mode autodiff is a compiler pass (lowered to LLVM IR). My goal is to treat model parameters as explicit, growable memory buffers. Since NOMA compiles to standalone native binaries (no Python runtime), it allows using realloc on weights mid-training. This makes "self-growing" architectures a system primitive rather than a complex framework hack. I just pushed a reproducible benchmark (Self-Growing XOR) to validate the methodology: it compares NOMA against PyTorch and C++, specifically testing how…
Dec 2025 · github.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →