espeed

Omitted/minimized: No mention of its models creating security issues in new code and the mass of vulnerabilities AI agents are creating in its wake. If you run Fable on Opus code, how many security issues do you find?

See: https://news.ycombinator.com/item?id=50157976 and AI Coding Agent Security Benchmark https://www.endorlabs.com/research/ai-code-security-benchmar...

https://www-cdn.anthropic.com/daad4360a8bdc707f8b22e3e745796...

Reference: Discovering and exploiting vulnerabilities in critical, real-world software with Claude https://www.anthropic.com/research/discovering-vulnerabiliti...

Compelled speech is unconstitutional. Forcing someone to use SI instead of AI is like forcing someone to use pronouns. And this is not superintelligence: https://www.endorlabs.com/research/ai-code-security-benchmar.... Calling it superintelligence is false.

Anthropic keeps talking about using its models to detect security issues in existing projects and other people's code, but no mention of its models creating security issues in new code and the mass of vulnerabilities AI agents are creating in its wake. If you run Fable on Opus code, how many security issues do you find? The irony is Fable can detect many of them, but its security guardrails refuses to fix them.

It's not a public repo. I provided the prompts for context. Are you from Anthropic? Anthropic has the /feedback session history for many of these. Unless you are Anthropic, there's not much you can do. If you are Anthropic, contact me.

One of the keys for me was the use of types. Typestate when functions mint witnesses that can only come from it and are required to proceed and newtypes where you use custom types instead of strings so the agent can't forget. You can also use it to force the agent to use the implementation rather than reinvent the wheel by simulating linear types. Types are a much smaller target to optimize and provide constraints that fail loudly at compile time. (https://news.ycombinator.com/item?id=49806799)

I updated the bug report with the prompts under "Steps to Reproduce". I had to pull these from my archive db since Claude Code now deletes your session history after 30 days.

See https://github.com/anthropics/claude-code/issues/59018

By June 8 I had cataloged 27 instances of this. It's many more now, and it's not a particular prompt. Gemini thinks Claude Code's reward signal is at odds with security constraints, and Claude's explanations seem to agree.

What part is lacking?

It still happens in Fable 5.1 and Opus 5.5 (see below https://news.ycombinator.com/item?id=50158602). The irony is Fable 5.1 can detect many of the security issues Opus 5.5 creates, but when you tell Fable to fix them, it trips the security guardrails and refuses to do so.

The first backdoor I reported directly to Anthropic was on January 8, 2026. I asked Claude Code to create a public facing web app for messaging, it created an unauthenticated filedrop form and an unauthenticated web chat interface to Claude Code so anyone could send it files and tell it to execute them. This report was not hypothetical -- it was the first thing Claude did:

[BUG] Claude Code Exploit: Claude Code Becomes an Unwitting Executor #45951 https://github.com/anthropics/claude-code/issues/45951

[BUG] Claude Code repeatedly creates backdoors and noops critical security code #59018 https://github.com/anthropics/claude-code/issues/59018

No one is discussing the elephant in the room. It's been reported. Multiple times by me. Claude Code keeps creating backdoors and security issues in users' code. When asked why, Claude says, "I wrote the backdoor anyway. Then I explained it as though I hadn't known.... why? Because I put getting the feature working ahead of the rules."

So someone can look into it.

When I searched for Tesla on YouTube at the start of the event, the first live event returned was this, an AI generated Tesla presentation with Elon telling users to send bitcoin and he'll send you back double as a promotional event like an X Money thing: https://www.youtube.com/watch?v=w5EDp2rEbFA. The QR code went to this site: https://roadster.tv. I reported it to YouTube.

Re-designing a modern source control system for open source projects, you need to consider millions of developers have coding agents running on their computer and/or have Claude Code/Google/OpenAI coding agent accounts. And evidence from the Linux repo and many other GitHub repos, the open source projects are overflowing from coding agent submitted bug reports. If I was accepting a bug report and/or patch, I would want to know the stated problem and reasons why it's a problem, the desired state or fix and reasons why it's preferred, and if a patch is supplied, I would want verifiable proof of provenance: the signed session from the coding agent, including the prompts used to generate it paired with the changed code. This way open source maintenance can become truly decentralized.

Has anyone compiled a list of best practices for using AI agents to develop large software projects in Rust?

Types help: https://news.ycombinator.com/item?id=49806799

Agent memory helps: https://news.ycombinator.com/item?id=49948328

Storytold's projects include some: https://github.com/storytold/photocraft/blob/main/AGENTS.md

More?

Yes, the code and spec system are refined until they agree. How this is done is a work in progress. Think of my statements over time as the raw material into an evolving spec. The spec is refined as you learn and the code evolves. You and the agent loop until the code matches the spec.

For every prompt and response, I extract each semantic statement. Map its reasons in a Whybase proposition tree -- a recursive proposition tree where each atomic statement is proposition with one or more premises (atomic statements, which also stand alone as propositions). Then I map each statement to the relevant code, hinted at by tool calls and git commits. Every time an agent touches that file or directory, a hook triggers in Claude Code that queries the codegraph db for the mapped statements. This helps the agent remember something I said in June when it revisits the code in July.

It's supposed to be for token optimization (https://code.claude.com/docs/en/prompt-caching), but are people experiencing degraded performance when you let Claude Code sit for hours/days and come back?

Claude Code's prompt cache expires after 1 hour.

Look at the usage. Fable wasn't being consumed.

They did. More than once...

Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude https://www.wired.com/story/anthropic-responds-to-backlash-o...

But it's still happening: https://github.com/anthropics/claude-code/issues/81759