Dagens Vibes — 31. maj 2026

Peter Steinberger 🦞@steipete

I do this with codex all the time. Ask it to review code for bugs and it will tell you all good, tell it there is a bug and it will LOOP AND LOOP and will find issues.

Peter Steinberger 🦞@steipete

With GPT 5.5, /goal, autoreview and crabbox my prompts moved from ~30-60min to often 4-10h tasks and my confidence that it’s ready is much much higher. Yielding agents is a skill.

Dan McAteer@daniel_mac8

Codex Dynamic workflows are great. Try it out. 1. Go to GitHub link below 2. Copy install instruction 3. Type /dynamic to invoke the skill Recreates the same orchestration logic as Claude Dynamic Workflows. > Generates orchestration script. > Spins up a swarm of subagents. > Enters /goal mode to complete the task. Free and open source.

Tom Blomfield@t_blom

Imagine replacing 90% of your employees with a team of geniuses who have no idea how your company operates. Total chaos. Nothing works. That’s what AI feels like today. The missing piece is extracting all the domain knowledge from people’s heads and providing that as structured context to the models.

BOOTOSHI 👑@KingBootoshi

GOD i've slept on mining my own chats to reference them for so long i've relied on writing everything down to docs and MDs now i'm telling agents to go read their own agent history because every chat log is a chronological story of everything i'm working on and moving towards it is the best memory system for developing i have on me right now i've noticed a lot of devs are mining their slack chats and using slack for this too which is a great use case it really is an exponential factor that the more chat history you have to reference, combined with the capabilities of the newest models and agents has become VERY powerful for simply talking to them and moving forward how can we index this efficiently ? has anyone basically QMD'd their Claude Code/Codex sessions? do you guys just have them grep? right now i'm having them rip through grep and they're just soooo good at it by default it's wild this is so silly to write out because it seems so obvious everything beyond a strong system prompt + current context + ability to search through chats for agent memory feels like a distraction

Chubby♨️@kimmonismus

A team of former DeepMind researchers just raised $50M to build an AI lab built around recursive self-improvement at the level of the whole research organization, not only a single model. Index and Radical co-led, NVIDIA's venture arm is in, and angels like Dwarkesh Patel, Thomas Wolf and Max Jaderberg are on the cap table. The founders have the track record to back it up. Louis Kirsch comes out of the Schmidhuber lineage on self-improving systems. Edward Hughes has argued that open-endedness is essential for artificial superhuman intelligence. Tantum Collins worked on AI policy in the Biden White House. Their idea is simple and big at the same time. Today's models are great at answering questions, but real discovery also depends on knowing which questions are worth asking. Inherent wants AI that works right next to humans inside that loop, as a collaborator and not only a tool. They call it living within the experiment. They also set it up as a Public Benefit Corporation, so the mission is written into the company from day one. This is the direction a lot of us have been hoping for, and one of the more credible attempts at recursive self-improvement I've seen so far. Really excited for it.

Georgi Gerganov@ggerganov

llama.cpp now has an official website: llama.app Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications. While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine). We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.

Tibo@thsottiaux

When we go from GPT-5.0 -> GPT-5.1 -> ... -> GPT-5.5, the number incrementing goes with improvements in capabilities and token efficiency (which translates to speed gains). With GPT-5.5 our best model yet. A simple strategy that we would like to continue.

antirez@antirez

I tested the freshly released Step 3.7 Flash model against DeepSeek v4 Flash. 1) Build a small Redis-alike server. 2) Write a recursive DNS server for local use. 3) Write an HTTP proxy. 4) Write a JSON parser. All tests with OpenRouter API, reasoning to high, no tokens limits.

Brad Lynch@SadlyItsBradley

Steam Machine’s welcome tour was added to Steam’s Backend last night https://t.co/draQoA4Fba