AI & Engineering at @particle_news, @syngspace alum.
Sidney, British Columbia
Joined March 2007
- Tweets15.4K
- Following1.5K
- Followers1.7K
- Likes11.1K
Pinned Tweet
This is probably as much fun as I'm going to get out of this iOS api... #SwiftUI
Nate de Jager retweeted
Apple's Core AI models repo is now accepting third-party contributions 🥳
If you have developed some cool ports, this is the best place to share your recipes with the community. Looking at you @JackdeS11 @mattt @kevinqz 😂
github.com/apple/coreai-mode…
Nate de Jager retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
Nate de Jager retweeted
Xcode 27.2 ships with a new skill for agents to work with Instruments, as well as an update to the SwiftUI specialist skill. Love that my apps can get better just by upgrading!
Nate de Jager retweeted
You ask. It listens. It answers. 🎧
Introducing Ask Ray, with Radar by @ParticleAPI.
Ray goes to work over Particle’s corpus of over 3 million enriched podcast transcripts, to find the answers to questions that matter.
Get the first month of Radar free using promo code: ASKRAY
Learn more: particle.pro/ask-ray?utm_sou…
Nate de Jager retweeted
Today we’re introducing Ask Ray in Radar.
Some of the most useful insights from experts, founders, and analysts are said out loud on podcasts, but finding the right moments has meant hours of searching.
Now you can find those insights within seconds. Ray researches across 160,000+ actively transcribed podcasts and answers with the exact moments it found, so you can press play and hear them for yourself.
First 100 people to sign up with code ASKRAY get their first month free.
Codex should have a Tupac-mode that posthumously finishes and releases my abandoned coding projects.
The biggest life-hack while vibe-coding: an enormous back-catalog of side projects and demo apps.
This is the most significant timesaver when applying AI engineering, because you can simply point it at a folder and say “I want this feature, like it was done here, copy it”. Software engineering isn’t usually about remaking the wheel. It’s about plumbing together known solutions to create new utility.
Being able to reference existing work is, IMO, the main skill when using agentic AI to assist with engineering. It scales all the way up to big projects when you have a highly standardised codebase (this is actually a thing, called Context Engineering).
I was able to utilise a bunch of reference code from previous projects I’ve worked on for the database, the shaders, and the Vision framework.
blog.jacobstechtavern.com
Nate de Jager retweeted
Important conversations are happening on podcasts, and now your agents using Exa can hear them 🎧
@ParticleAPI is Exa's provider of podcast data and intelligence, delivering on our mission to bring spoken conversation to agents everywhere.
Nate de Jager retweeted
Transcription and enrichment from a catalog of 24M+ podcast episodes, on demand.
(In addition to the 3.4 million we already have)
Harnessing the power of spoken conversation is easier than ever, with @ParticleAPI.
Today we’re introducing Episode Archive Transcription on Demand.
Particle currently transcribes 160,000+ podcasts as they publish, and we add thousands of transcripts daily to our corpus of over 3.4 million transcripts. Now you can request transcriptions on demand for an additional 24 million episodes not yet in our corpus, with transcripts ready within minutes.
Available now via API and MCP. platform.particle.pro
Nate de Jager retweeted
every launch vid now is like
*cavemen making fire*
*model t*
*wright bros*
*moon landing*
*nuclear bomb detonation*
“every great innovation was once called crazy… that’s why today we’re launching AI-powered automated accounts receivable for operationally complex services businesses”
Nate de Jager retweeted
Big news today from Apple: Keynote is getting an open, JSON-based file format (.keyx), plus a Python library to create Keynote files on any platform.
Pages, Numbers and Keynote files today are closed and hard to modify unless you use AppleScript (limited and old) or Shortcuts (a huge pain), so you can’t really use AI to make documents in those formats. This was a HUGE pain inside Apple as well as outside, and most tools worked around it by making a PowerPoint file and importing it into Keynote, which wasn’t perfect.
Creator Studio subscribers on the Mac also get MCP support in Keynote, Pages and Numbers, so you can bring your own AI agent to read, edit and automate all three. Both the new format and MCP support arrive in November.
Bringing an AI-friendly format to Keynote (and I assume Pages and Numbers soon after) is a big positive change.
Huge day for Creator Studio today.
Our new in-app assistants can help you get things done in record time. MCP allows you to bring your own agent if you want. And an open source format for Keynote (and Python library!) so you can create Keynote documents programmatically on any platform.
Super proud of the team. Hope you love it!
Nate de Jager retweeted
We let your agents listen. 🎧
@ParticleAPI is now a plug-in in @ChatGPT.
Go here to install it: chatgpt.com/plugins/plugin_a…
Sign up for Particle here: particle.pro?utm_source=sbt&…
