SouL

@albychok @raycast @peduarte Wallpaper?

The proper new @raycast experience: fly to Barcelona → bump into @peduarte → install the beta

@peduarte Drop it already @peduarte Love you man!

you have no idea how happy i am that the new raycast is finally out we can finally get back on our normal release and content schedule 101 things you can do with raycast? pffft. make it 1001 😮‍💨

@peduarte So cool

photo of the photo

@mitryco @raycast @peduarte @thomaspaulmann Register and wait. You will receive an invitation soon.

@soulcodesmith @raycast @peduarte @thomaspaulmann how to try v2?

Thank you for Raycast v2! 🎉 @raycast @peduarte @thomaspaulmann Quick take: Raycast is the best app ever made. I have never been more excited about an app than this one.

Google Official Skills just dropped. 13 skills released already — built around the Agent Skills standard and compatible with Claude Code, Gemini CLI, Cursor, Copilot, and more. Feels like the beginning of a real shared ecosystem for AI agents. github.com/google/skills

@raycast @peduarte @thomaspaulmann @peduarte @thomaspaulmann @raycast I'm hoping to get Glaze access too! 👀

@jglypt @raycast @peduarte @thomaspaulmann I guess you'll have to wait, mate.

@soulcodesmith @raycast @peduarte @thomaspaulmann i wanna get in!!

@thomaspaulmann @raycast Codex and Claude code

Distribution of coding agents at @raycast - what's your preferred one?

@MalvinCherianHW @Adidotdev lol

@Adidotdev Soviets have Telegram I guess.

-USA has ChatGPT -USA has Grok -USA has Claude -USA has Gemini -USA has Copilot -China has DeepSeek -China has Qwen -China has GLM -China has Kimi -China has MiniMax : ) What is the rest of the world even doing ?

@emanueledpt @IbrahimElkamali Okay, but what about terminal customisation? For example, change the font size? would be really helpful inside dpcode @emanueledpt

@igsoulpvt @IbrahimElkamali not at the moment im focused on cli providers now, like pi too coming soon

Cursor is coming soon to DP Code 👀

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons: 1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing. 2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM". The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc. 3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc. I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3). The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to... Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.

@thomaspaulmann @raycast I'm waiting, can you guys make it quick? I know you have been working on it, but give it to me 😌

AI Chat gets a major upgrade in the new @raycast: 🎨 Fresh new look 🥷 Built-in skills support ⚒️ Auto-loading extensions, MCPs, and skills 🖼️ Deeply integrated with macOS … plus plenty more.

@peduarte I've been waiting for years. @peduarte

it's already started started small to get initial feedback and fix anything that may come up (natural and expected in a new beta software) when feel comfortable releasing to a wider reach we'll make it publicly available shouldn't be long meanwhile we'll keep inviting more and more people

@alexi_build I'm waiting to get access to Raycast 2.0.

@igsoulpvt yeah, looking forward to use it more

New Raycast 2.0 now has memory! 🧠

@robinebers Should add Ollama too? By the way, thanks for this.

well that's new 😭 must be that new chronicle feature

@thomaspaulmann The hype is so real, can't wait to try it out!

Watch your inbox! Small group for now, more soon.