Viewing profile — steer_dev

Hi HN, I'm a senior MLE. I've been watching the hype around agent swarms and tools like Gas Town clash with reality of productizing them. I wrote this because I see companies burni…

The Data: Green Line (Capability): MMLU State-of-the-Art (48% → 94%). Red Line (Control): Organizations with effective mitigation for inaccuracy/hallucination (lagging at ~52%). So…

Author of the "Confident Idiot" post here ( https://news.ycombinator.com/item?id=46152838 ). After that discussion, I looked at my own agent code and realized it was 80% error hand…

AI Slop (apologies, filler) isn't just annoying; it is In-Band Signaling Noise. The model mixes control signals (persona) with data (payload). Prompting ("Be concise") is brittle. …

Doing post-mortems on my agent's failures over the holidays made me realize the problem isn't the model. It is the lack of a deterministic inference-time verification layer. I spen…

OP here. I’ve realized that a 3,000-token system prompt isn't "logic", it's legacy code that no one wants to touch. It’s brittle, hard to test, and expensive to run. It is Technica…

OP here. Last week I posted a discussion ("The Confident Idiot Problem") about why we need deterministic checks instead of just "LLM vibes" for reliability. That thread [1] blew up…

You're 100% right. For a "judgment" task like "Does this patient have cancer?", the final acceptance criteria must be a human expert. A purely deterministic verifier is impossible.…

Exactly. We treat them like databases, but they are hallucination machines. My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it. If we wr…

OP here. I wrote this because I got tired of agents confidently guessing answers when they should have asked for clarification (e.g. guessing "Springfield, IL" instead of asking "W…

Hey HN, I’m the author. I built Steer because I was tired of the 'Confident Idiot' problem—where agents output broken JSON or hallucinate facts, and I only find out when the app cr…