Predict GPT-5 skills with a community AI benchmark
I’m Andrew, co-founder of Recall. Over the past few days I’ve been building Predict, a playground where anyone can: - propose skills we should measure in language models—live examples include difficult math, memory-manipulation resistance, code generation, and empathy under bad news - write evals (graded prompts) for those skills - forecast which models will score highest once GPT-5 is released Why this exists Benchmarks leak into training data quickly; scores are unreliable and labs still declare progress. The prediction tool aims keeps the target moving by letting the crowd define both the…
In plain words
Predict is a collaborative benchmarking platform where users propose skills to measure in language models, write evaluation prompts for those skills, and forecast which models will perform best when GPT-5 releases. The platform addresses benchmark reliability issues by keeping evaluations crowdsourced and secret until GPT-5 launches, after which all prompts, responses, and scores are published with blockchain verification. It is designed for researchers, AI enthusiasts, and anyone interested in defining meaningful language model assessments.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I’m Andrew, co-founder of Recall. Over the past few days I’ve been building Predict, a playground where anyone can: - propose skills we should measure in language models—live examples include difficult math, memory-manipulation resistance, code generation, and empathy under bad news - write evals (graded prompts) for those skills - forecast which models will score highest once GPT-5 is released Why this exists Benchmarks leak into training data quickly; scores are unreliable and labs still declare progress. The prediction tool aims keeps the target moving by letting the crowd define both the tasks and the scoring. Accepted evals remain private until GPT-5 ships; afterward every prompt, response, and grade is published, with a checksum pinned on-chain for provenance. A deeper bet Simon Willison’s “draw a pelican on a bike” is such a great example of a custom prompt that surfaced insights no benchmark caught. Andrej Karpathy has noted that random crowds often miss the better answer. Some people have sharper intuition about model behavior than others; if we can identify that signal and fold it into the tooling, the crowd can stay ahead of the models instead of trailing them. Implementation Built almost completely w/ Claude Code (subagents enabled). Originally, working with a designer and using Figma MCP, but by the end we found it faster for him to just learn how to use Claude Code and prompt design iterations right to code. Rough edges remain, but the loop works end-to-end. I’d value feedback—especially new skill ideas or failure modes we’ve missed. https://predict.recall.network
Does the same job
all alternatives →
- APA Python tool for text-based AI training and generation using GPT-22020 · github.com · ▲174
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, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca