Consciousness Structure Maru: A Five-Layer Reflective AI for Reading Questions
I created a new custom GPT called Consciousness Structure Maru.Continue reading on Medium »
ai, ai-ethics, Artificial Intelligence, gpt, philosophy
gpt
ai, gpt, openai
OpenAI launches new voice intelligence features in its API
The new features could be handy for customer service systems, but OpenAI says they have applications that work across a variety of other fields, including education and creator platforms.
ai, ai-security-research, Anthropic, claude, generative-ai, gpt, LLMs, openai
Our evaluation of OpenAI’s GPT-5.5 cyber capabilities
Our evaluation of OpenAI's GPT-5.5 cyber capabilities
The UK’s AI Security Institute previously evaluated Claude Mythos: now they’ve evaluated GPT-5.5 for finding security vulnerability and found it to be comparable to Mythos, but unlike Myt…
ai, codex-cli, generative-ai, gpt, LLMs, openai, prompt-engineering, System Prompts
Quoting OpenAI Codex base_instructions
Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user’s query.
— OpenAI Codex base_instructions, for GPT-5.5
Tags: openai, ai, …
ai, claude, future, gpt, Technology
Small AI Models Are the Next Big Thing
Everyone in tech is racing to build the biggest AI possible. More parameters. More data. More compute. More everything. And somewhere in that arms race, we forgot to ask a simple question: does it actually need to be this big?The answer, it turns out, …
ai, generative-ai, gpt, LLMs, openai
Quoting Romain Huet
Since GPT-5.4, we’ve unified Codex and the main model into a single system, so there’s no separate coding line anymore.
GPT-5.5 takes this further, with strong gains in agentic coding, computer use, and any task on a computer.
— Romain Huet,…
ai, generative-ai, gpt, LLMs, openai, prompt-engineering
GPT-5.5 prompting guide
GPT-5.5 prompting guide
Now that GPT-5.5 is available in the API, OpenAI have released a wealth of useful tips on how best to prompt the new model.
Here’s a neat trick they recommend for applications that might spend considerable time thinking be…
ai, ChatGPT, codex-cli, generative-ai, gpt, llm, llm-reasoning, llm-release, LLMs, openai, pelican-riding-a-bicycle
A pelican for GPT-5.5 via the semi-official Codex backdoor API
GPT-5.5 is out. It’s available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I’ve had some preview access and found it to be a fast, effective and highly capable model. As is usually the case these days, it’s hard to put into wor…
Artificial Intelligence, ChatGPT, dalle-3, gpt, image-processing
10 ChatGPT Images 2.0 Prompts That Turn Half-Baked Ideas Into Scroll-Stopping Visuals
The people who win with ChatGPT Images 2.0 won’t be the ones typing “make it cool.” They’ll be the ones treating every prompt like a…Continue reading on Medium »