Alternatives
Products that do what 70 days, 800 stars. If AI bugs are not random but math inevitable? does
hi all. i’ve been shipping a small open project that tries to answer that question with evidence, not vibes. in 70 days it reached \~800 stars. the core claim is simple: many AI failures are not noise. they repeat because the geometry and ordering underneath are stable. if so, we should be able to name each failure mode, set acceptance targets, and stop shipping the same bug twice. ### what it is * a compact Problem Map of 16 reproducible failure modes in RAG and agents. * each item has a minimal fix and measurable gates. examples: * Semantic ≠ Embedding: metric and normalization mismatch.…
- 1SF
Hi HN, Over the past two years I’ve built and debugged a fair number of production pipelines—mainly retrieval‑augmented generation stacks, agent frameworks, and multi‑step reasoning services. A pattern emerged: most incidents weren’t outright crashes, but silent structural faults that slowly compromised relevance, accuracy, or stability. I began logging every recurring fault in a shared notebook. Colleagues started using the list for post‑mortems, so I turned it into a small public reference: 16 distinct failure modes (semantic drift after chunking, embedding/meaning mismatches,…
2025 · github.com
- 2
- 3SO
hello everyone, my first post! AA here, founder of ⌘ Langbase.com — we are a developer platform for building and scaling serverless AI memory agents. I know surveys can be boring, but this one’s different—it’s interactive! That's very much intentional. My team and I have been up for the last 21 hours putting together this report. This was a looot of work, so I hope y'all like it. Introducing … State of AI Agents 2024 report On Langbase, we processed 184 billion tokens and handled 786 million AI agent runs from 36K developers. From all that data plus insights from 3.4K builders who filled out…
2024 · langbase.com
- 4SA
Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the outputs by weighting segments based on confidence. Low entropy in the output token probability distributions correlates with accuracy. High entropy is often where hallucinations begin. My dad Scott (AI Research Scientist at TRI) is my research partner on this. He sends me papers…
Mar 2026 · sup.ai
- 5
- 6W1
Hey HackerNews, I built this project over the last few weeks as a palette cleanser from a failed game launch. I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate. Well - I couldn't, but I got pretty close. 14 Bytes total model size, and a 96.5% solve rate on unseen mazes. Trained across 46 phases experimenting with different ideas to improve the model (better performance, smaller size). Its quite fun to watch the model attempt to solve the maze, when they fail its usually due to getting stuck in a…
Jul 2026 · con-dog.github.io
- 7IP
To be specific, the content is generated by a GPT-2 based model. https://amzn.to/2TCc0v2 Let me know if you have any questions :-)
2020
- 8AH
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
- 9
- 10ME
We are building a VM that helps you simulate realistic production conditions, model latencies, different interleaving, user requests, and find bugs. Every non-deterministic property is turned into a knob you or a coding agent can control. We have helped teams perfectly reproduce support incidents and found bugs in some of the world's most well tested software (including a database).
Jun 2026 · workers.io
- 11DS
Hi HN! Today me and qianli_cs want to share a new open-source project we've been working on called Durable Swarm. It's a drop-in replacement for OpenAI’s Swarm that augments it with durable execution to make your agentic workflows resilient to failures, so that if they are interrupted or restarted, they automatically resume from their last completed steps. https://github.com/dbos-inc/durable-swarm We believe that as multi-agent workflows become more common, longer-running, and more interactive, it's important to make them reliable. If an agent spends hours waiting for…
2024 · github.com
- 12
- 13IS
Hey HN! For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester. The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism. No Auo-Gen, Langchain and Crew AI - Everything custom built for pentesting. Each test runs in an isolated Kali linux environment (on AWS Fargate), where the agents have full access to the environment to undertake any…
2025
- 14
Hello all, I'm a software developer. Over the last few months more and more of my work has turned into using coding agents instead of typing the whole code myself. Usually a few claude sessions at once, sometimes codex, one per feature or per revealed bug. I ran them in a split terminal for a few weeks, and quickly spotted two main problems. The first is that I couldn't easily tell which agent was stuck waiting on me and which was still working, so I'd cycle through sessions and checking on them. The second one: agents sharing a single branch step on each other. Two of them could be editing…
Jul 2026 · shikigami.dev
- 15AB
Hey everyone, My friend and I built a simple bug fixing app that listens for alerts/issues from Sentry, contextualizes it against your codebase, and any other data sources you wish to connect (right now we support Notion, Google Docs, and Slack), and deploys an ai agent to write a PR for review in Github or Gitlab to solve the bug. Our current demo shows the end-to-end process for a trivial bug fix, but we have been testing it with open source python repos like http-pie, comparing how our agent solves a bug compared to a human engineer and it gets fairly close. We are working on adding…
2023 · resolvd.ai
- 16IB
Hey HN, I've made a groundbreaking discovery: procrastination can lead to questionable projects! While avoiding real work, I somehow created a directory of 130+ AI agents and frameworks. It's like I tried to organize a robot party and everyone showed up. What's inside: - A list of AI agents - Frameworks to build more agents So, HN, before I spiral into an existential crisis: did I accidentally create something useful, or should I go touch grass? P.S. If this somehow becomes the next big thing, I promise to pretend it was intentional all along.
2024 · aiagentsdirectory.com
- 17FC
Hi everyone, I’ve been working on an open-source tool called Flakestorm to test the reliability of AI agents before they hit production. Most agent testing today focuses on eval scores or happy-path prompts. In practice, agents tend to fail in more mundane ways: typos, tone shifts, long context, malformed input, or simple prompt injections — especially when running on smaller or local models. Flakestorm applies chaos-engineering ideas to agents. Instead of testing one prompt, it takes a “golden prompt”, generates adversarial mutations (semantic variations, noise, injections, encoding edge…
Jan 2026
- 18
- 19AA
I'm a VP of Engineering with 20 years in the field. I've been thinking deeply on why AI is breaking every engineering practice, and it led me to the conclusion that the Agile Manifesto's values need updating. The core argument: AI made producing software cheap, but understanding it is still expensive. The Manifesto optimizes for the former. This addendum shifts the emphasis toward the latter. Four updated values, three refined principles, with reasoning for each. Happy to discuss and defend any of it.
Mar 2026 · github.com
- 20MC
Hi HN, I’ve been building AI agents and copilots, and kept running into a frustrating problem: they don’t fail loudly, they forget things quietly. Users re-explain preferences, agents contradict earlier responses, and context resets without any clear visibility into why. I built Memograph CLI as a debugging tool to analyze conversation transcripts and show: - what the agent forgot - where continuity broke - contradictions and repeated context - estimated token waste due to re-prompting It works locally and supports plain text or JSON transcripts. Example: $ memograph Output: Cognitive Drift…
Feb 2026
- 21TN
Hi guys, I’m excited to share an update on ReproModel, an open-source toolbox designed to streamline the testing and reproduction of machine learning models. I, like many of you, have really struggled with benchmarking and comparing models, from missing code, to opaque experiment parameters slowing the process. I decided to take matters into my own hands, and created a mini-toolbox in my free time to streamline the process. The goal is to reduce the time and effort spent on replicating experiments, enabling researchers to focus on innovation rather than setup. Knowing this task is not an…
2024 · github.com
- 22AS
I made a strategy game where you play the US or China through the AI race, 2026 to 2030, sixteen quarterly turns in the browser. One run takes about half an hour. At the start, the game seals two dice you never get to see. Inside: how hard alignment really is, and how fast takeoff compounds. You get eval reports, but only as ranges, and they flatter you most exactly when your systems are least aligned. At the end you get a debrief which shows what your evals said each quarter and also what was actually true. I lost every run I played myself so far. Every number in the game is source-backed…
Jul 2026 · criticalwindow.org
- 23IB
The main goal of this was to be able to not just run multiple Claude Code sessions at once, but actually manage them and keep track of what I was doing. Sometimes this is multiple attempts on the same task, sometimes I work several tasks at once. Really I was just sick of twiddling my thumbs waiting for the coding agent to finish, and I wanted it to be easy to work on/review/test another change while I waited.
2025 · github.com
- 24IG
Hello HN, I work on vision systems for structural inspection. A common pain point is usually that while we have a lot of "healthy" images, we often lack a reliable "Golden Set" of rare failures (like shattered porcelain) to validate our models before deployment. You can't trust your model's recall if your test set only has 5 examples of the failure mode for example. So to fix this, I built a pipeline to generate datasets. In this example, I took 7 real-world defect samples, extracted their topology/texture, and procedurally generated 200 hard-to-detect variations across different…
Feb 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →