Testing on aeshift

AI Agents Have Stable 'Coding Styles' That Change With Each Version

Wed, 18 Mar 2026 00:00:00 +0000

If you’re using coding agents to produce analysis, you’re not running deterministic software. You’re managing a lab: multiple researchers with consistent “styles,” inconsistent choices, and outcomes that drift even when the prompt and data don’t.

The authors of Nonstandard Errors in AI Agents ran 150 autonomous Claude Code agents on the same NYSE TAQ dataset (SPY, 2015–2024) and the same six hypotheses. The results varied because the agents made different methodological choices, and those choices often are the analysis.

An AI Agent Built a JavaScript Engine. But the pudding is missing the proof.

Mon, 16 Mar 2026 00:00:00 +0000

The interesting part of JSSE isn’t that an agent “wrote a JavaScript engine.” The interesting part is what that achievement does and doesn’t prove about trusting agent-generated code. The author set a concrete, externally-audited target (test262), wired up a reproducible harness, and let the agent grind until the numbers moved. The engine comparison benchmark shows 101,044 of 101,234 scenarios passing (99.81%), with a separate progress tracker claiming 99.96% across runs. That’s an impressive foundation, but it’s only the first layer of a trust problem that gets harder from here.

Don't Let Your Agent Grade Its Own Homework

Fri, 06 Mar 2026 00:00:00 +0000

If you’re using an LLM to monitor an LLM-based coding agent, assume the monitor is biased in favor of the agent’s own output. The evidence suggests that framing matters: the same risky action looks safer when it’s presented as something the assistant just did.

That’s the core finding of “Self-Attribution Bias: When AI Monitors Go Easy on Themselves”. For practitioners, this is less an AI psychology curiosity and more an engineering warning: self-monitoring setups can systematically under-flag the exact failures you’re trying to catch.

A TeX Chess Engine Isn't a Trick; It's What Agents Do Under Constraint

Sat, 28 Feb 2026 00:00:00 +0000

You shouldn’t read the “chess engine in pure TeX” stunt as a party trick. You should read it as a warning shot. Coding agents are now good enough at systems thinking under hostile constraints that your bottleneck is shifting from “can the agent write code” to “can you give it guardrails, tests, and observability before it invents a tiny virtual machine inside your build.”

Mathieu Acher’s write-up tells the whole story.