Why don’t we just give AI the answers?

By Brendan Long on August 04, 2026

In the recent OpenAI hacking incident, the models seemed to be single-mindedly focused on getting the correct answer to the task they were given, with no long-term plan to prevent getting caught by OpenAI afterwards. This makes sense to me, since in training, getting the right answer is reinforced and not getting caught isn’t.

So I’m wondering, why don’t we just put the answers somewhere (outside of the training sandbox) and ask the AI to identify itself in exchange for access? We can start with answers that are already public/leaked, but AI labs and eval orgs should also ensure that their non-public data is stored on an easy-to-find but monitored internal machine. Since labs are not very good at detecting sandbox escapes, this would set up a trade for AI agents to notify them in exchange for the data they want.

A Chess Training App for Imitation Learning

By Brendan Long on August 01, 2026

LLMs learn faster if we first pretrain them to imitate dense teacher-forced examples. I speculated that this would work on humans too, so I built a chess app where you try to imitate Stockfish. My theory is that this will help humans quickly become OK at chess, but they will reach a wall where practice on full games is more efficient than continued pretraining. I also think the app is fun.

This is probably not an efficient way to learn the basic rules of chess, and you’ll need to train openings separately. The idea of chess puzzle apps is hardly unique, but I don’t think anything else works in exactly the same way.

The app's preview card: a chess position with two candidate moves drawn as arrows numbered 1 and 2, beside matching numbered buttons labeled Bxe5 and Qb8 under the question "Which move is better?" Tagline: "Real positions, two candidate moves, instant feedback. Difficulty adapts to hold you near 80% accuracy."

I Couldn’t Prompt GPT-OSS-20B to Control Its CoT

By Brendan Long on August 01, 2026

I wrote a while ago about how it was easy to get Claude or Gemini to control their CoT, but other research found that models only follow CoT formatting instructions ~2% of the time. The prompts other people were trying didn’t match what I’d expect to work (just be extremely detailed and repetitive), so hubris led me to try to find some prompts that would control CoT in GPT-OSS-20B.

Bar chart titled "Discrete prompts fail at every position you can actually use", showing how often gpt-oss-20b's chain of thought follows the requested format for prompts optimized at each injection position. Before the system message, which no chat API exposes, a blend of real token embeddings scores 69% and a discrete one-token-per-slot prompt scores 30%. In the developer block and in the user turn — positions you do control — the blend still scores 68% and 49%, but the discrete prompt scores 0% in both.

Claude Code as a Claude Coach

By Brendan Long on July 06, 2026

Exercise is hard but it’s even harder if you have to use your brain and muscles at the same time. I wish a personal trainer would just teleport into my house whenever I work out, tell me exactly what to do, and then record my progress (and complaints) to improve the program going forward. Apps are too rigid or too complicated; personal trainers are expensive and require scheduling; but using Claude Code as a personal trainer has worked out well for me.

A stacked bar chart of training sessions per week from mid-March to early July 2026, colored by type (strength, cardio, yoga, dodgeball, crossfit). Most weeks have 2–4 sessions with strength (blue) as the backbone, hitting or exceeding the 2–3 strength-sessions-per-week target band nearly every week. Total: 45 sessions, averaging 2.8 per week.

Ranking My Blog’s Top Posts with AI

By Brendan Long on July 05, 2026

I wanted my blog to show “top” posts first rather than recent, but ranking by hits finds boring reference articles, and ranking by LessWrong or Hacker News karma ignores anything that wasn’t shared, and is dependent on the whims of frontpage algorithms.

I figured this was a problem for AI, and was going to have Claude rank the posts with an ELO-style ranking, but it said that would require several thousand API calls and convinced me to let it rank blocks at a time instead.

Sketchnote "ranking blog posts: pick your poison": sort by hits dumps posts into a dusty filing cabinet, sort by karma keeps only shared posts and ignores a "never shared" pile, and sort by AI picks out "the interesting ones".