AdaptGauge
Detect when few-shot examples make your LLM worse
What it does
AdaptGauge detects when adding few-shot examples degrades LLM performance instead of improving it. Testing 8 models across 4 tasks revealed three failure patterns: • Peak regression — 64% at 4-shot, crashed to 33% at 8-shot • Ranking reversal — best zero-shot model dropped to third with examples • Selection collapse — TF-IDF examples broke a model from 50%+ to 35% Tracks learning curves, auto-detects collapse, classifies patterns, and compares example selection methods. Demo results included.
Does the same job
all alternatives →- CAChainForge, a visual tool for prompt engineering and LLM evaluation2023 · chainforge.ai · ▲177
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! :)
- ILImprove LLM Performance by Maximizing Iterative Development2024 · github.com · ▲104
I have been working in AI space for a while now, first at FAANG with ML since 2021, then with LLM in start-ups since early 2023. I think LLM Application development is extremely iterative, more so than any other types of development. This is because to improve an LLM application performance (accuracy, hallucinations, latency, cost), you need to try various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, different agent architecture, and more. There are thousands of possible combinations and you need a process…
- OSOpen-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…
- IT“Is this loss?”: A TensorFlow Lite app to detect Loss.jpg2018 · ▲82
I built this app over a week as a way to learn how to use TensorFlow with Mobilenets and to get some experience with Google Play (and partly as a dare). It's written in Java, as I wasn't able to find a Kotlin API for TFLite. It was built with Bazel. I'm pretty satisfied with the actual detector's performance, although I expect I could improve the UI a little bit. It's a weird UX, as you want it to be as simple and fast as possible (loss/notloss) but you also want it to have some sort of recognizability. I would love to hear your thoughts.…
- BABuild an open-source computer vision model in seconds using text2023 · usezeroshot.com · ▲64
Hello HN! I want to share something me and a few friends have been working on for a while now — Zeroshot, a web tool that builds image classifiers using text-image models and autolabeling. What does this mean in practice? You can put together an image classifier in about 30 seconds that’s faster and more accurate than CLIP, but that you can deploy yourself however you’d like. It’s open source, commercially licensed, and doesn’t require you to pay anyone per API call. Here's a 2 minute video that shows it off: https://www.youtube.com/watch?v=S4R1gtmM-Lo How/why does it…
- ILImprove LLM Performance by Maximizing Iteration Speed2024 · palico.ai · ▲5
LLM Application development is extremely iterative, more so than any other types of development. This is because in addition to all the activities involved in regular application development, we also need to make the LLM Application accurate and reduce hallucination. To improve performance, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, try different agent architecture, and more. There are thousands of permutations to try. We need to be able to easily experiment with these…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
