Click any tag below to further narrow down your results
Links
The author, a veteran hardware and software hacker, walks through how they use AI agents with Ghidra, radare2, and Python/Rust tooling to reverse engineer devices and software far faster than they could by hand. The post pairs a workflow (documentation files, a hypothesis-testing loop, probes and logging) with a list of projects like custom synth firmware and camera control apps.
- The workflow has the agent document findings in markdown files and run a hypothesis loop (state a guess, design an experiment, record the result) to stop it going in circles.
- The author uses DeepSeek with Ghidra's MCP bridge, and says current models handle raw x86 or ARM disassembly reasonably well.
- Claimed results over six months include firmware for Arturia MiniFreak, Teenage Engineering OP-Z, and Akai MPC Sample, plus wireless control of Sony Alpha cameras.
- The author stresses that human expertise is still needed to steer agents away from narrow, unproductive approaches by reading their reasoning traces.
CodeAF is a Go-based coding harness from AgentField AI, built to run coding agents on open models cheaply and manage several projects from one window. It is in early preview and Apache 2.0 licensed.
- On the DeepSWE benchmark, using the same DeepSeek model, its senior-dev specialist solved more issues than nine other harnesses, including Claude Code and Codex, at the lowest cost per solved issue.
- It runs as a single small binary with nothing else to install, and one window shows every project, conversation, and running task on the machine.
- Work is split across a planner, worker, and checker model per task, and changes land on their own branch, never on main, only after they pass checks.
This is an index page listing every post Sean Goedecke has tagged "explainers," covering topics like LLMs, DeepSeek, Model Context Protocol, blockchain, diffusion models, and interpretability. It's a jumping-off point rather than an article with a single argument.
- The index is dominated by AI topics: how LLMs and ChatGPT work, DeepSeek's cost and reasoning work, MCP, and interpretability.
- Blockchain shows up several times, including a Stripe "Tempo" FAQ and beginner-level primers.
- A few posts fall outside AI and blockchain, such as how to read code, code review mistakes, and writing technical explanations.
@ruima on X
A translated Renwu profile of Moonshot AI, the three-year-old Beijing startup behind the Kimi chatbot, based on 100 hours of access to its office. It covers the company's flat, title-free culture, its hiring around "taste" and generalist talent, and how the DeepSeek shock in early 2025 pushed it to focus on models.
- Moonshot AI has about 300 employees, a valuation above RMB 120 billion (roughly $16 billion), and no departments, titles, OKRs or KPIs; reporting lines are very simple.
- Hiring leans heavily on referrals and "taste," and on people who can generalize across roles; more than half of the 30 employees interviewed had changed jobs multiple times.
- The DeepSeek release in late 2024 hit Kimi hard, and the company responded by narrowing its focus to model capability, which staff describe as "in a way, DeepSeek saved us."
- The author raises the open question of whether the flat structure can scale past a few hundred people, and notes that the lack of clear goals can leave individuals feeling adrift.