Will Lamerton

Very proud of this Nanocoder release - big contributions from all corners of the community and the software is getting reallllyyyy good 🔥

Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI

Bless it's little 0.8b socks. Qwen3.5:0.8b is really cool but, this will forever get it lol

Nanocoder 1.23.0 is out 🚀 Interactive prompts. Scheduled task automation. Graceful shutdown. Better stability. New file ops. Readline keybinds. And so much more. Your local-first AI coding assistant just got way better. github.com/Nano-Collectiv…

@FollowBenParry asked last week "What's been the hardest technical problem so far" for Whisper... After the last few days, I'd say how we safely update user's JSON data between App versions is a contender Ended up creating `json-up` - a new NPM package to solve migrating JSON (github.com/Nano-Collectiv…)

Modeled from my very own cat Tiddles. He deserves to be centre-stage 😜

@mickythompson @npmjs @npmstatus Same here @npmjs @npmstatus

@npmjs @npmstatus We are experiencing 'registry.npmjs.org/-/npm/v1/secur… error (500). Will retry in 10 seconds. 2 retries left.' when using pnpm audit.

@jonymusky @npmjs Same here @npmjs @npmstatus

Hey @npmjs npm audit endpoint returning persistent 500 Internal Server Error

@ds_bakshi @npmjs Same here @npmjs @npmstatus

Hi @npmjs, npm audit is throwing 500 error.

@NicoKlein10 It's interesting! I don't actually have either of these on any of my projects. It appears to be failing everywhere. That's the error locally and in CI:  `WARN  post registry.npmjs.org/-/npm/v1/secur… error (500). Will retry in 10 seconds. 2 retries left.`

@willlamerton I've narrowed this down to these dev dependencies on our project: eslint plugins, and svelte language server. Removing those stops the issue. Still investigating - but any other insights would be helpful

npm auditing is down. no status. 500 error.

Fine-tuning tiny models is one of our strategies to bring private, local AI up alongside the models that come from big tech. The output of this research will bring direct value to both @UseWhisperAI and the software being built in @nano_collective. There's so much R&D to do in this space - every day you're learning.

I recently gave GLM-5 a spin on their coding plan. It was very slow creating a few section landing page in about 20 minutes. It got me thinking about the efficiency gain though. Even just a few years ago, creating a landing page of the calibre GLM-5 did would have taken hours most likely to code from scratch. Crazy we're complaining about that being shrunk to 20 mins. But, in todays coding agent landscape, that's down to a couple of minutes so even 20 mins is now slow.

Thanks @Kimi_Moonshot - love how keen you are to help with coding 😳

Kimi K2.5 one shot this chess game. I gave it two more prompts after this, one to amend colours and one to add a full AI opponent. Which it did easily. Mad. Full video soon.

Kimi K2.5 mid-creation of 5x6 chess. Fast. Efficient. Video out soon.

A very cool release of Nanocoder. Lot's of improvements all around 🥳

When the coding agent you started is good enough to be your daily driver. Open source made this happen.

We went open source with @UseWhisperAI last week - a huge step. We want Whisper to be a community project where we can build private AI for everyone and open sourcing what we have is a cornerstone to this!

Working on sexy new git tools for Nanocoder. Makes git operations intelligent, simple and intuitive.