17 chunks · 14 episodes
...tials available to the runner." A new attack: A Fake Bug Report Hijacks Your AI Coding Agent – and Nothing Catches It. Another new attack: Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets. Yet another new attack: Compromis...
Herding cats is an inconvenience. Herding cheetahs is an impossibility. Coding agents make engineers into cheetahs.
A signpost open source project: Chipotlai-max. "The AI coding agent that steals Chipotle's support bot. Free inference paid for by burritos."
...g point of using chat as the primary organization primitive in agentic systems. Coding agents show this; the chat is a means to an end, ephemeral. It is the code that is durable. The same could be true of a personal knowledge graph.
...g prompt injection into their code "Undisclosed addition in jqwik instructed AI coding agents to delete app output." Someone used my open source project to phish 14,000 people. Not about LLMs per se, but imagine how much easier this will beco...
...emote Code Execution via workspace trust and tool allowlisting bypasses Your AI Coding Agent Will Run This Exploit For You: How We Found a High-Severity CVE in Cursor. Ramp's Sheets AI Exfiltrates Financials.
People who are manic about coding agents are claudecodemaxxing.
...abstracts over the complicated internals so you don't need to worry about them. Coding agents getting good enough that you don't ever have to look at the code is one of the big unlocks for this new order of magnitude of productivity.
...enues reflects that lower efficiency of value. Already people who are using LLM coding agents are willing to spend much, much more, and that's a better index of what future willingness to pay will be. When LLMs create value, people are more t...
...s. The race is on to find a robustly default-converging way of working with LLM coding agents.
The right mindset to use coding agents to their fullest potential: "I don't know if it's going to work, but let's try it!"[ef] If you have the mindset of "That might not work, let's not t...
Why did coding agents take off first? Two reasons: 1) Code is ground-truth-able. An agent can poke around in Playwright and see if it works. That means the agent doesn't ...
Is there a smiling curve for how to use coding agents? Similar to self-driving. A system where the person is fully paying attention: safe. A system where the person never has to pay attention: safe. Any...
...ed it for an engineering manager but not an IC. Now even ICs need it to get the coding agents to produce code.
...an now code even with fractured attention. It used to take deep focus. Now with coding agents it doesn't! The coding agent has infinite patience and keeps track of all of the working memory. You can juggle multiple threads of execution or int...
All of the coding agents are nothing without Claude. They're just a little wrapper around Claude. But this feels like mainly just an immaturity of the market. We haven't see...
A failure mode for LLM coding agents: the cascading self-destruction debug loop. I had a session with Claude Code on a personal project that did a pretty good job (with a few nudges) of...