Sign in

William (Bill) Kennedy

@goinggo.net
2.2K followers 183 following 457 posts

⌯Go ⦁ Walking the line between correctness and comprehension ⦁ bill@ardanlabs.com ⦁ kronkai.com ⦁ wife(aleintech.com) ⦁ GoBridge

PostsRepliesMedia
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 2h
One week to go! 🦾 GoSF is back in San Francisco on October 7th, with @goinggo.net talking about Self-Hosted LLMs in Go. Go, AI, networking, & community. 📍 Antithesis 🕠 5:30 PM PDT 👉 www.meetup.com/golangsf/eve...
011
Reposted by William (Bill) Kennedy
deadprogram @deadprogram.com · 8h
@squillace.bsky.social did you see my recent jeyzma.com yet?
jeyzma.com
Jeyzma - Go with your own intelligence
Go with your own intelligence. System One decisions, 100% local in your browser.
034
William (Bill) Kennedy @goinggo.net · 23h
Bystander Society by @aleintech.com alekennedy1.substack.com/p/bystander-...
alekennedy1.substack.com
Bystander Society
The Cornell 7, group chat apathy, and the quiet death of empathy in modern culture.
000
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 24/09/2026
Yesterday, @goinggo.net joined the GolangNYC Meetup in New York City. Great conversations, a room full of developers, and plenty of ideas shared around building with Go. Thanks to everyone who came out and made it a great meetup! 📸 Sharing a few moments from the event below.
031
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 17/09/2026
Go + AI is coming to NYC! Join @goinggo.net at GolangNYC on Sept. 23rd for networking / a talk from his Ultimate AI curriculum to explore what building AI systems with Go can look like. 📍 New York City 📅 September 23rd | 6-8pm RSVP: www.meetup.com/golanguagene...
012
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 16/09/2026
What if your Go application could handle AI inference directly? @goinggo.net walks through the #Kronk Model Server and how it handles: → Local & remote GPU inference → Real-time VRAM monitoring → In-Memory Caching → Hugging Face models → Speech + image generation 🎥: youtu.be/Sv0ZhQjaa1M
youtu.be
Kronk AI Model Server Overview: Go-Native AI Inference, Web UI & Context Caching
YouTube video by Ardan Labs
011
William (Bill) Kennedy @goinggo.net · 17/09/2026
v1.32.7 Released Version 1.32.7 brings image generation into the model server with new API endpoints and BUI screens, a new OpenAI-compatible audio translation endpoint, Wan2.2 S2V audio-conditioned video support in the Malina SDK, and llama.cpp upgrades through b11017. github.com/ardanlabs/kr...
github.com
Releases · ardanlabs/kronk
Go With Your Own Intelligence! Use Go for hardware accelerated local inference with llama.cpp, whisper.cpp, and stable-diffusion.cpp directly integrated into your Go applications. Kronk provides a ...
040
William (Bill) Kennedy @goinggo.net · 15/09/2026
If you are in the SFO area on Wednesday Octber 7th I will be speaking at the Go meetup and talking about all things #Kronk and #golang. www.meetup.com/golangsf/eve...
meetup.com
Go meetup in San Francisco | Hosted by Antithesis, Wed, Oct 7, 2026, 5:30 PM | Meetup
Hello GoSF! Let's meet other gophers, learn, and have a good time! Hosted by [Antithesis](https://antithesis.com/). \# Agenda * **🤝** 5:30 PM - 6:00 PM: **Welcome and ne
031
William (Bill) Kennedy @goinggo.net · 14/09/2026
Quick overview of the #Kronk model server.
041
Reposted by William (Bill) Kennedy
FOSDEM @fosdem.org · 14/09/2026
fosdem.org
FOSDEM 2027 Call for Stands
🚀 FOSDEM 2027: Showcase Your Open-Source Project to the World
01711
Reposted by William (Bill) Kennedy
deadprogram @deadprogram.com · 14/09/2026
Thank you very much to #cupOGo for having me as a guest last Friday to talk about @tinygo.org Check it out here: cupogo.dev/episodes/a-b... #golang #tinygo #embedded
cupogo.dev
Cup o' Go | A big episode about tiny things
golang.org/x/tools v0.50.0 releasedBlog: Finding unreachable functions with deadcode by Alan Donovan Russ Cox leaves google, and opines on LLMs for debugging Coding agent guidelines for modern Go J...
094
William (Bill) Kennedy @goinggo.net · 10/09/2026
Version 1.32.6 Released llama: b10896 whisper: v1.9.3 stablediff: master-849-d04e895 kronkai.com
kronkai.com
Kronk — Local LLM Inference for Go
Hardware accelerated local LLM inference for Go with llama.cpp integration.
010
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 09/09/2026
YouTube short of the week is here!💻 This week revolves around “Choosing Priorities in a Career Path” from @goinggo.net t 's podcast episode with featured guest Jonathan Amsterdam! 🤓 🎥: youtube.com/shorts/IhkkO... #ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
youtube.com
Choosing Priorities in a Career Path
YouTube video by Ardan Labs
021
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 04/09/2026
That’s a wrap on GopherCon LATAM! 🇧🇷 Thank you to everyone who joined us, stopped by, and shared conversations with the Ardan Labs team. A special thank you to the organizers, @goinggo.net , and the Ardan Labs engineers who attended and made the conference a great experience. Until next time! 👋
021
William (Bill) Kennedy @goinggo.net · 07/09/2026
Check out the new #Yzma website and try Yzma in the browser while you are there! #golang yzma.ai
yzma.ai
yzma
yzma lets you write Go applications that use llama.cpp for local inference with full hardware acceleration.
052
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 01/09/2026
@goinggo.net is kicking off a workshop: Ultimate AI, at @gophercon.com LATAM today. 🇧🇷 A room full of engineers, Go + AI, and lots of hands-on learning. Here are a few snapshots from the workshop 👇 #GopherConLATAM #golang #ArdanLabs
051
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 01/09/2026
YouTube short of the week is here!💻 This week revolves around “Discovering Go While Working at Google” from @goinggo.net's podcast episode with featured guest Jonathan Amsterdam! 🤓 🎥: youtube.com/shorts/FZLlb... #ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
youtube.com
Discovering Go While Working at Google
This clip is from the Ardan Labs Podcast with featured guest Jonathan Amsterdam! You can watch the full episode here: https://youtu.be/CNT_9FaVIHI Other Links: Website:…
031
William (Bill) Kennedy @goinggo.net · 26/08/2026
Checkout the current family of #Kronk stickers coming to a #golang event near you. Check out the travel schedule on the Kronk repo. github.com/ardanlabs/kr...
010
William (Bill) Kennedy @goinggo.net · 26/08/2026
In my neverending attempts to make these models behave well enough for real usage, @dlsniper shared these non-thinking settings with me this morning and I have to say the model is usable today. That can change by the hour, but it's usable!
000
Reposted by William (Bill) Kennedy
Talking Heads From The Year 2053 @talkingheads2053.com · 26/08/2026
The AI takeover continues in Episode Two. In this scene special guest star @boursiquot.com asks Phineas a question with hilarious results. See the only show with robot actors run on @officialarduino.bsky.social UNQ Q boards & @golang.org / @tinygo.org code on @github.com youtu.be/Pny5TFP2r3U
065
William (Bill) Kennedy @goinggo.net · 26/08/2026
#Kronk v1.32.1 Released Removes the adaptive MTP draft-count algorithm and its runtime reporting. MTP speculative decoding now always runs with the configured fixed `ndraft` value, while classic separate-draft speculation retains its acceptance-EMA adaptive throttling.
021
William (Bill) Kennedy @goinggo.net · 25/08/2026
#Kronk v1.32.0 published Brings adaptive draft-count tuning for MTP speculative decoding, an upgrade to llama.cpp (yzma v1.25.0), new codegen-benchmark tooling, and fixes to GLM tool parsing and embedded MTP compatibility detection. github.com/ardanlabs/kr...
github.com
Releases · ardanlabs/kronk
Your personal engine for running open source models locally. Use Go for hardware accelerated local inference with llama.cpp and whisper.cpp directly integrated into your Go applications. Kronk prov...
110
William (Bill) Kennedy @goinggo.net · 25/08/2026
Latest installment of Talking Heads From The Year 2053 - Episode Two has been released by @deadprogram.com www.youtube.com/watch?v=Pny5...
youtube.com
Talking Heads From The Year 2053 - Episode Two
YouTube video by Talking Heads From The Year 2053
010
William (Bill) Kennedy @goinggo.net · 25/08/2026
I wrote a program that uses OpenCode to have different models write a Go based tic-tac-toe game. This take a wee bit of time to run for all models. The Gemma4 and the Qwen3.8 models always do well. I wish the Qwen3.8 ran faster. Tomorrow Qwen3.8 Flash is being released!
010
William (Bill) Kennedy @goinggo.net · 24/08/2026
Here is the "fun" kronk has to deal with for you. ndraft=3 for MTP works great for Qwen/Gemma but not for Ornith. Ornith works better with ndraft=2. llama.cpp hardcodes 3. Kronk uses an adaptive algorithm that can downgrade from 3 to 2 based on sampling, so Ornith runs faster.
120
William (Bill) Kennedy @goinggo.net · 24/08/2026
This is a simple example of why you need to be looking at diffs when the model/agent is making code changes. This is why vibe coding is going to cause all sorts of problems over time with codebases. There needs to be a human in the loop.
192
Reposted by William (Bill) Kennedy
Jesús Espino @jespino.bsky.social · 24/08/2026
My new article, the Kronk SDK, is live. 3 important components: → prep: messages validated, templated and tokenized into a job → KV cache: restore the prefix, decode only what's new → engine: makes your tokens tick concurrently internals-for-interns.com/posts/kronk-... #golang #AI
internals-for-interns.com
The Kronk SDK | Internals for Interns
In the previous article we took yzma apart and found a very disciplined bridge: purego finds the functions inside libllama.so, libffi makes the calls, and no C compiler is involved anywhere. What you...
012
William (Bill) Kennedy @goinggo.net · 19/08/2026
Ok Kids, new release of Kronk coming soon to fix some performance issues. This model is outstanding and the best I've seen in a long time. It's a Qwen based model published about a month ago. It has been better than the Qwen3.8 27B for sure. huggingface.co/unsloth/Orni...
huggingface.co
unsloth/Ornith-1.0-35B-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
031
William (Bill) Kennedy @goinggo.net · 19/08/2026
Get ready #golang v1.27.0 will be released today! groups.google.com/g/golang-ann...
011
William (Bill) Kennedy @goinggo.net · 19/08/2026
v1.31.5 release of #Kronk now available. Best version yet. Plus updated website with new Bucky and Malina pages. kronkai.com
031
William (Bill) Kennedy @goinggo.net · 18/08/2026
Latest version of #kronk released today gives you a view of how the slots are running and the IMC caches. Check it out!
010
Reposted by William (Bill) Kennedy
Association for Computing Machinery @acm.org · 13/08/2026
In this week’s People of ACM, Russ Cox, who was the technical lead at the Go programming language for over a decade, gives us a behind-the-scenes look at the popular programming environment. Read the full interview here: www.acm.org/articles/peo...
0389
William (Bill) Kennedy @goinggo.net · 15/08/2026
Mind blown 🤯 Turned off thinking for the Qwen3.8, for the Q8 and Q4 versions. Agent performance is now very acceptable and I have not seen this model create a bad first version of the tic-tac-toe game. The Qwen3.6 Q8 runs lighting fast, but never perfect like Qwen3.8.
010
William (Bill) Kennedy @goinggo.net · 15/08/2026
Mind blown 🤯 Turned off thinking for the Qwen3.8, for the Q8 and Q4 versions. Agent performance is now very acceptable and I have not seen this model create a bad first version of the tic-tac-toe game. The Qwen3.6 Q8 runs lighting fast, but never perfect like Qwen3.8.
000
William (Bill) Kennedy @goinggo.net · 15/08/2026
Update from my earler Qwen3.8 27B post. #Kronk release v1.31.1 - Increased performance by 10% via MTP changes. - Turned thinking off and now the model is usable and completing tasks better than Qwen3.6. The model over-reasons even in low mode unfortunately.
110
William (Bill) Kennedy @goinggo.net · 15/08/2026
My analysis with Qwen3.8 using #kronk and game prompt using the UD-Q4_K_XL version on a M5/128GB. Model is slow (10 TPS) and over reasons in low mode, but it has back-to-back wrote a perfect game with the undo feature. MTP is running. At this speed it's a hard model to use.
020
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 11/08/2026
It’s workshop day at @gophercon.com UK! 🇬🇧 Great to see so many developers joining the workshops with @goinggo.net & Florin Pățan, diving into practical conversations around Go, AI, and production systems. Real engineering. Real tradeoffs. Real systems. A few moments from the workshops 👇
031
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 10/08/2026
Ardan Labs Connect UK is underway! 🇬🇧 We’re in London in partnership with Ravelin for an evening of networking, technical discussions, & community. Right now, @goinggo.net is taking the stage to talk about: Self-Hosted Inference in Go: No Python, No CGO, No Network Hop Here’s some snapshots👇
011
William (Bill) Kennedy @goinggo.net · 10/08/2026
Malina support in Kronk produced this image. prompt: a small red sailboat crossing a calm mountain lake at sunrise
052
William (Bill) Kennedy @goinggo.net · 10/08/2026
Don't remember where I saw this, but it's holds so very true. Especially in this age of agent based engineering. "The cost of productivity is bugs. Nothing is free."
031
William (Bill) Kennedy @goinggo.net · 10/08/2026
New versions of Bucky, Malina, and Kronk released. All projects running on the latest versions of their respective ggml based libraries. Basic Malina api support coming to kronk as experimental. New mascots (Malina and Kuzco)
010
William (Bill) Kennedy @goinggo.net · 09/08/2026
Missed a regression that happened with the code I published under v1.30.4. Took me a few hours to figure out what code changes caused it to happen. I'm upset I didn't catch it before I merged. Testing models are tough and many lessons have been learned. v1.30.5 is on its way!
010
William (Bill) Kennedy @goinggo.net · 08/08/2026
Kick Ass job as always by @jespino.bsky.social on the release notes for 1.27. It felt overwhelming. I'm wondering if Go fix can be used to change Go code with some of these changes like struct literal field selectors and maybe switching to the new uuid package? victoriametrics.com/blog/go-1-27/
victoriametrics.com
Go 1.27 interactive tour
An interactive tour of what’s new in Go 1.27: every notable language, runtime, and standard library change, with short runnable examples you can edit and run in the browser.
084
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 07/08/2026
🇬🇧 @goinggo.net is coming to London for a FREE in-person event Join us at Ardan Labs Connect: UK, hosted in partnership with Ravelin Complimentary food and beverages will be served; enjoy them during the networking sessions! 🎟️ www.eventbrite.com/e/ardan-labs... Limited capacity. Register early.
eventbrite.com
Ardan Labs Connect: UK 2026
Join us for a chill meetup where tech minds connect, share ideas, and spark new projects at Ardan Labs Connect: UK 2026.
011
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 07/08/2026
🙏 Thank you, @gophercon.com US, what an incredible week! A huge thank you to everyone who visited the Ardan Labs booth, attended @goinggo.net and Florin’s sessions. If we didn’t get a chance to connect, we’d love to hear from you. 📩 www.ardanlabs.com/contact/ See you at the next GopherCon! 👋
ardanlabs.com
Ardan Labs | Contact Us
Contact Ardan Labs to discuss software engineering training, consulting, staff augmentation, or development in Go, Rust, Kubernetes, and AI.
031
Reposted by William (Bill) Kennedy
Ardan Labs @ardanlabs.com · 03/08/2026
Meet @goinggo.net & attend his talk at a free in-person event in London! 🇬🇧 Join us for Ardan Labs Connect: UK on Monday, Aug 10th 🎟️ Register free: www.eventbrite.com/e/ardan-labs... Note: Tickets are limited due to venue capacity. Please register early to secure your spot!
eventbrite.com
Ardan Labs Connect: UK 2026
Join us for a chill meetup where tech minds connect, share ideas, and spark new projects at Ardan Labs Connect: UK 2026.
011
Reposted by William (Bill) Kennedy
deadprogram @deadprogram.com · 06/08/2026
First up @goinggo.net lightning talk about kronkai.com here at @gophercon.com #gophercon #golang #llm #llamacpp
0103
William (Bill) Kennedy @goinggo.net · 31/07/2026
6.5 hour flight to Seattle for @gophercon.com with NO WIFI or ENTERTAINMENT! My local model better step up and do the job! 😂
110
Reposted by William (Bill) Kennedy
deadprogram @deadprogram.com · 31/07/2026
Here we go, the journey to @gophercon.com has begun! #gophercon #golang #tinygo
Flight cases covered with stickers
2154
William (Bill) Kennedy @goinggo.net · 29/07/2026
Best version of #Kronk ever! v1.29.7 Now is a great time to build some #golang apps and services using open source models. www.kronkai.com
kronkai.com
Kronk — Local LLM Inference for Go
Hardware accelerated local LLM inference for Go with llama.cpp integration.
183