👨💻Engineering AI systems for AJ Hackett Bungy in New Zealand 🏗️ Building dev tools in public.
New Zealand
Joined June 2022
- Tweets3.5K
- Following990
- Followers1K
- Likes3.1K
how much do you spend on AI coding a month?
$0: free models + opencode
$20: one sub
$100-200: max plan
$500+: you're either shipping or cooked
mine: $30 👀
Everyone's setting up Grok Bot. Then they look at the empty box and think: "ok... now what?"
So I made 5 ready-to-use bots you can copy and paste:
📥 Inbox brief
📅 Meeting prep
🧾 Weekly expense sweep
🔔 Price/listing watcher
📄 Research-to-doc
Free: codermatt.gumroad.com/l/vaoe…
How to connect @Instaboxsh and @AmpCode using self-hosted orbs!
Matt retweeted
$100k to the developer who can make muse spark open fastest!
We're launching a $100,000 challenge to see who can make Muse Spark run fastest: openkernelchallenge.dev/
been thinking about why fast type checkers matter more for agents than for us
I run tsc a few times an hour. an agent runs it after basically every edit, reads the errors, tries again
so the checker's speed kinda is the agent's speed
say an agent checks 50 times in one task. that's ~12 mins sitting around on the old tsc vs ~20s on tsrs
and that's before linters, tests and builds, which agents hammer too
if you maintain an open source project you can apply for 6 months of ChatGPT Pro from OpenAI, free
Codex included, plus API credits
and their page says use it in OpenCode, Cline or pi too 👀
apply here: developers.openai.com/commun…
needs a public GitHub profile and a public repo. it's reviewed on a rolling basis so not everyone gets in, but some pretty small projects have
this graph is just my heart rate on a bungy platform
+50% week over week is wild @getpancake_ai, congrats Will 🥞
it's been 10 weeks of 50% week-over-week growth with pancake.ai
no matter how many startups you’ve built, the next one still makes you feel like a beginner. there’s always something you’ve never done before that you suddenly need to figure out.
jumping out of a plane, trying to break a guinness world record. it's all fun!
but the best part is still realizing you’ve built something other people think is worth paying for.
more to come!
you can run a 122B coding model on a 64GB Mac now
@ornith_ 1.5 came out this morning under MIT and @atomic_chat_hq already has a 47.6GB quant up for it
free and fully offline 👀
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
full list:
MiniMax M3.1 Flash
DeepSeek V4.1 Flash
GLM-5.3-Flash
LongCat 2.5 Preview
Beam
MiMo-V2.6-Flash
MiMo-V2.5
Nemotron 3 Ultra
Nemotron 3.5 Lightning
Nemotron 3.5 Super VL
Exo
Jev 1.13
Big Pickle (stealth)
LL Alpha (stealth)
all limited time. the stealth ones may use your data
opencode.ai/v2/docs/console/…
