I added image generation to my coding harness so it can tell me little stories as I work. Today it noticed Remembrance Day and made this
Workdays can blur together. Small, unexpected moments like this make one feel distinct enough to remember
7
352
Hey someone at @github why is this button always broken? This is in a draft PR with inline draft comments
243
Still ❤️ Zellij and PI
Top-right pane has an ongoing story. Every 30 min, the next scene picks up where the last left off, weaving in world events and whatever I’m working on
It starts with `/avatar SOME PROMPT` in PI but then evolves
🤖 Made with AI
This harness leaderboard is interesting
huggingface.co/spaces/joelni…
2
324
This sounds dumb, but it’s a real unlock: make coding agents put code in the right folders. Your folder structure is documentation they already latently know about
6
6
664
This is nuts if true
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.…
7
477
Told a civil engineer that AI writes all my code now. His jaw dropped. I wonder if he saw his own job drastically changing in the same way as mine has or did he realize programmers might someday be obsolete?
1
1
493
Pretty happy to see this. Lots of good memories in this building
obj.ca/shopify-signs-new-lea…
1
8
2,124
Love the momentum around System One models
a brand new model paradigm! introducing 𝚌𝚕𝚊𝚒𝚛𝚒𝚌: a system one model for extracting, computing, estimating, and predicting values from unstructured inputs.
blog.cloudflare.com/clairic-…
2
447
Starting to wonder if “pair programming” with AI could ease the PR review bottleneck
Gathering context makes people say, “I’ll review this tomorrow.”
🤖 Made with AI
3
4
443
I think a year from now it’ll feel quaint that we were editing SOUL.md just to coax a bit of dry humour out of our coding agents
I feel like we need to vibe-code one of these
🤖 Made with AI
2
5
418
I’ve been working on a bunch of AI initiatives at @Opendoor. Hard problems. Lots to build
If you’re in Toronto and curious, come chat with me, @MargaretSyms, and @EyalKlein1 and others on October 7
Limited spots: docs.google.com/forms/d/e/1F…


















