Alternatives
Products that do what APE: Predictive EdTech Architect does
Transform static LMS into predictive learning ecosystems.
- 1L3
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
- 2MM
Hi HN! Erik here from Pig.dev, and today I'd like to share a new project we've just open sourced: Muscle Mem is an SDK that records your agent's tool-calling patterns as it solves tasks, and will deterministically replay those learned trajectories whenever the task is encountered again, falling back to agent mode if edge cases are detected. Like a JIT compiler, for behaviors. At Pig, we built computer-use agents for automating legacy Windows applications (healthcare, lending, manufacturing, etc). A recurring theme we ran into was that businesses already had RPA (pure-software scripts), and…
2025 · github.com
- 3IM
Hi, I'm a high school teacher from Australia and I've built what I'd like to think is a pretty nifty ChatGPT powered presentation tool for teachers. I'd love it if you could have a look at it and give me some of your feedback. I don't think there's much overlap with the HN crowd and school teachers, but I've been coming here for many years and thought I'd post here and see what you all think. Check it out if you have a minute and I'd be super happy to hear your feedback too. https://www.slidehero.ai/ You can jump in and have a play with the tool all you like ;) Cheers, Eli
2025
- 4
- 5
- 6
Talk to Static, a public AI shared by everyone. There are no separate copies: what it learns from one conversation can shape another.
21d ago · wildstatic.com
- 7
- 8OS
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
- 9OS
We implemented Stanford's Agentic Context Engineering paper which shows agents can improve their performance just by evolving their own context. How it works: Agents execute tasks, reflect on what worked/failed, and curate a "playbook" of strategies. All from execution feedback - no training data needed. Happy to answer questions about the implementation or the research!
Oct 2025 · github.com
- 10PG
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…
2025
- 11MR
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
- 12
- 13IT
Dec 2025 · github.com
- 14CC
Yesterday I built something that probably shouldn’t exist yet. In 9 hours, I created a cognitive architecture demonstrating emergent reasoning. It follows a 5-step loop: Plan → Reason → Act → Reflect → Respond. Adding a WebSearchTool to test extensibility, the agent initially failed its first search, reflected on poor results, adapted its query, and then succeeded. This behavior wasn’t programmed; it emerged naturally from the architecture. Five hours later, I integrated a FileManagerTool — it worked on the first try. Like code compiling first time, except this was intelligence composing…
2025 · github.com
- 15LT
I’m excited to share a project I’ve been working on for over a year, which I believe will fundamentally change our approach to language models. We’ve designed a new architecture, which replaces the hidden state of an RNN with a machine learning model. This model compresses context through actual gradient descent on input tokens. We call our method “Test-Time-Training layers.” TTT layers directly replace attention, and unlock linear complexity architectures with expressive memory, allowing us to train LLMs with millions (someday billions) of tokens in context. Our instantiations, TTT-Linear…
2024
- 16
- 17IM
Every time I wanted to use LLMs in my existing pipelines the integration was very bloated, complex, and too slow. This is why I created a lightweight library that works just like scikit-learn, the flow generally follows a pipeline-like structure where you “fit” (learn) a skill from sample data or an instruction set, then “predict” (apply the skill) to new data, returning structured results. High-Level Concept Flow Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps And the bast part: Every step can be saved and reused as…
2025 · github.com
- 18MA
Hi HN, I'm a solo developer learning to code, and I'd love to share my second real project: MapMyLearn, an AI-powered app that automatically generates personalized learning paths based on any topic you input. What it does: Takes a topic (e.g. "history of capitalism", "learn Rust", or "data storytelling") Uses AI to break it down into a structured course with modules and submodules Each submodule includes: - Detailed, pedagogical content (developed based on online sources to mitigate hallucinations) - A quiz of 10 questions - Recommended resources - An AI chatbot for Q&A - Optional audio…
2025
- 19ΤB
τ-Bench is an open benchmark for evaluating AI agents on grounded, multi-turn customer service tasks with verifiable outcomes. It's been great to see the community adopt it since launch — this is now the third iteration. With τ³-Bench, we're extending it to two new settings: knowledge-intensive retrieval and full-duplex voice. τ-Knowledge: agents must navigate ~700 interconnected policy documents to complete multi-step tasks. Best frontier model (GPT-5.2, high reasoning) hits ~25%. The surprising part: even when you hand the model the exact documents it needs, performance only reaches ~40%.…
Mar 2026
- 20PS
I didn't want to buy a standalone computer or repurpose a laptop to run constantly so I could maintain a system to sync my LLMs, so I built this. It's a simple overview of my system, laid out in a way easy to unpack and replicate for yourself. The project is meant to be configured individually, and uniquely, since one solution might not be what's best for another. If anything, maybe it gives you some ideas on how to implement things for your own project. Best wishes, Ryan.
28d ago · pacslate.com
- 21AH
This paper formally defines where current AGI hits a structural wall — not a technical one. It shows that no amount of scaling, reinforcement learning, or recursive optimization will break through three deep epistemological and formal constraints: 1. Semantic Closure — An AI system cannot generate outputs that require meaning beyond its internal frame. 2. Non-Computability of Frame Innovation — New cognitive structures cannot be computed from within an existing one. 3. Statistical Breakdown in Open Worlds — Probabilistic inference collapses in environments with heavy-tailed uncertainty.…
2025
- 22DA
We made this for our school project. I think we went a little too ambitious.
2023 · github.com
- 23CA
Hey HN, Cole and Alex here. We're excited to share CourseGen (https://www.CourseGen.ai), an AI-powered platform that aims to rethink the traditional approach to education by utilizing generative AI models for creating individualized learning paths. If you're into AI, education, and how these two can intersect, you might find this interesting. The backbone of CourseGen is the generative AI. Instead of the one-size-fits-all courses, CourseGen aims to craft tailored, non-linear learning paths. Think of it like a choose-your-own-adventure book, but for learning. We acknowledge that…
2023
- 24HA
Hi HN, I am Umer. I recently built an experimental framework called HyperFlow to explore the idea of self-improving AI agents. Usually, when an agent fails a task, we developers step in to manually tweak the prompt or adjust the code logic. I wanted to see if an agent could automate its own improvement loop. Built on LangChain and LangGraph, HyperFlow uses two agents: - A TaskAgent that solves the domain problem. - A MetaAgent that acts as the improver. The MetaAgent looks at the TaskAgent's evaluation logs, rewrites the underlying Python code, tools, and prompt files, and then tests the new…
Apr 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →