AethrionX
AI product manager with institutional memory
What it does
In March, your senior engineer spent a week figuring out how to build your search system. She ruled out the obvious queuing approach — too slow, too expensive at scale — and picked something better. She wrote it all down. She left in October. Last month, a new engineer started rebuilding the same system using the exact approach she ruled out. Six months of work, repeating a solved mistake. AethrionX would have shown him her research the moment he opened the ticket.
Does a similar job
all alternatives →
Deep Work PlanJun 2026 · deepworkplan.com · ▲114Models matter. Context matters more. Give your agent a plan.
- HSHiDimensional – senior engineers recommend candidates to startups2017 · ▲29
Hi HN! We’re excited to share with you the public beta launch of our startup, HiDimensional (www.hidimensional.com). We are a platform consisting of senior engineering leaders who interview candidates and provide recommendations of the best candidates and their strengths. We then use the recommendations to refer these candidates to founders of startups that match their strengths and interests. The recommendation serves as a personal referral from the interviewer, so for candidates, it amplifies their application and fast-tracks them through the process. And for companies, they are receiving…
- BYBenchmark your eng team's AI agent maturity in 5 minutesJul 2026 · agent-benchmarks.com · ▲14
we had hundreds of discussions with engineering leaders over the past few months, and everyone's trying to understand where they are in the AI journey. we collected all this data into a benchmark and built a free grader to let you know where you stand. you answer on a 1–5 scale (e.g., autonomy runs from "suggestions only" to "agents own multi-hour workflows across code, infra, and external systems") - takes about 5 minutes. https://agent-benchmarks.com/software-factory/ waiting for your results!
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 · 19d 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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
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…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com