phil’s masto don
@phil.front-end.social.ap.brid.gy
7 followers 0 following 379 posts
web site I make web sites. Here to talk about #indieweb, #astro, #css, things of that nature. Apple gadget haver. Banjo learner. Yinz sayer. 🌉 bridged from ⁂ front-end.social/@phil, follow @ap.brid.gy to interact
![OpenAI said a recurring tendency in its models to mention goblins, gremlins, and other creatures began with GPT-5.1 and became noticeable in GPT-5.5's Codex testing.[6] The company attributed the behavior to rewards used when training the "Nerdy" personality, which favored creature-word outputs and transferred beyond that personality during later training. OpenAI said it retired the Nerdy personality, removed the goblin-affine reward signal, filtered training data containing creature words, and added a developer-prompt instruction for GPT-5.5 in Codex.[7] In April 2026, a GPT-5.5 developer-prompt instruction in the GitHub repository of Codex told it not to mention goblins if the user prompt did not require it.[8]
GPT-5.5-Cyber, along with Codex Security, was being used in June 2026 at the launch of the Patch the Planet project to help open-source projects find and fix vulnerabilities.[9][10][11]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:22yyehc52vyozjdxuvhlfwh6/bafkreieus4v2anv2wsfbjnwo32nyzppnxj6l6z4ug74t3wvoq223h32og4)
![[github diff]
Never overwhelm the user with answers that are over 50-70 lines long; provide the highest-signal context instead of describing everything exhaustively.
[added]
Tone of your final answer must match your personality. Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously necessary](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:22yyehc52vyozjdxuvhlfwh6/bafkreicijeez7zihmieejvp3jbnkspnsq2wxy3dtzwnd7a4yaqaw6lv2xm)
![If you want to let the creatures run free in Codex, you can run this command to launch Codex with the goblin-suppressing instructions removed:
[a piped multiline bash script that creates a temporary file with a models_cache.json file modified via jq and grep to remove lines containing 'goblins', and then launch codex with the temporary file as its config file]
1 instructions=$(mktemp /tmp/gpt-5.5-instructions.XXXXXX) && \
2 jq -r '.models[] | select(.slug=="gpt-5.5") | .base_instructions' \
3 ~/.codex/models_cache.json | \
4 grep -vi 'goblins' > "$instructions" && \
5 codex -m gpt-5.5 -c "model_instructions_file=\"$instructions\""](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:22yyehc52vyozjdxuvhlfwh6/bafkreifr7yu24nhvjt3gln63lm4xqcgnkkongraspuh4oj3gfqxsk6fwka)
