Alignment Is Hard at Scale

Zvi surveys opines on evals, chain‑of‑thought, confession training, and the fragility of oversight techniques.

Play episode from 01:21:22

chevron_right

Transcript

chevron_right

Transcript

Episode notes

The cycle of language model releases is, one at least hopes, now complete.

OpenAI gave us GPT-5.1 and GPT-5.1-Codex-Max.

xAI gave us Grok 4.1.

Google DeepMind gave us Gemini 3 Pro and Nana Banana Pro.

Anthropic gave us Claude Opus 4.5. It is the best model, sir. Use it whenever you can.

One way Opus 4.5 is unique is that it as what it refers to as a ‘soul document.’ Where OpenAI tries to get GPT-5.1 to adhere to its model spec that lays out specific behaviors, Anthropic instead explains to Claude Opus 4.5 how to be virtuous and the reasoning behind its rules, and lets a good model and good governance flow from there. The results are excellent, and we all look forward to learning more. See both the Opus 4.5 post and today's update for more details.

Finally, DeepSeek gave us v3.2. It has very good benchmarks and is remarkably cheap, but it is slow and I can’t find people excited to use it in practice. I’ll offer a relatively short report on it tomorrow, I am giving one last day for more reactions.

The latest attempt to slip unilateral [...]

---

Outline:

(01:47) Language Models Offer Mundane Utility

(02:51) Language Models Don't Offer Mundane Utility

(04:14) On Your Marks

(05:21) Get My Agent On The Line

(06:02) Advertising Is Coming

(07:30) Deepfaketown and Botpocalypse Soon

(13:43) Fun With Media Generation

(15:11) A Young Lady's Illustrated Primer

(16:33) You Drive Me Crazy