DeepSeek V4.1 Flash and the 890 bytes that matter for agents
Live on Helmcode, replacing V4 Flash at no extra cost. It redesigns inference for a workload that keeps growing: agents that read far more than they write.
AI
16 posts
Build your own Granola with open models
Record and transcribe your meetings with open models, turn them into structured data, and build a searchable memory of every conversation you have had.
GLM 5.3 is now available on Helmcode
GLM 5.3 ties Kimi K3 at the top of the open models and runs on our European infrastructure with 1M of context and the same 150 euros a month.
Does building your own infrastructure to run open models pay off? We did the maths
An 8x H200 node serving GLM-5.2 costs €25,250 a month before it serves a single token. The full numbers, the break-even, and when owning the hardware wins.
Which open model for which job
Eleven open models solve the 80 enterprise use cases in our guide. The three axes that decide which one, and fifteen cases with theirs next to them.
Cordis: the paper behind the DeepSeek Harness architecture
The five theorems in the Cordis paper, the plugin framework behind DeepSeek Harness, explained in plain language and with what already runs in production.
What a town hall of 20,000 residents can do with AI
What a small town hall actually automates with open models: filings, minutes, notices, grant calls and by-laws, with human review kept in place.
Watermarking and the AI Act, explained: how it affects you as a company, as a developer, and what happens with open models
Anthropic is going to watermark Claude's text, and the reason is Article 50 of the AI Act. What it requires, who it binds, and what changes with open models.
GLM 5.2 orchestrates, DeepSeek V4 Flash executes
How to design multi-model systems where one open LLM plans, another executes, and the context they hand each other stays efficient.
GLM 5.2 is now available on Helmcode
GLM 5.2, the 744B MIT open model, now runs on Helmcode's European infrastructure with zero logs and a flat rate of 150 euros a month.
The AI Act explained: what actually applies in August
The calm version of the AI Act: which obligations really apply to you from 2 August, which ones the Omnibus moved, and what to have ready.
Which GPU do you need to serve AI models
FP8, NVFP4, H200, B200: what each NVIDIA generation accelerates in hardware, how much VRAM your model needs, and which GPU to buy. With real production data.
NaN: the community's first month in numbers
117 billion tokens, 3.68 million requests, 21 countries, and 99.98% uptime. NaN is a community of builders with its own inference infrastructure and a private platform to deploy apps and agents.
How to set up an inference server to serve AI models
In this post I'll walk you through how the community's inference servers are set up: the hardware we use, the stack we run, and the models we serve.
Claude Code for DevOps
I've spent several hours over several days documenting and optimizing my entire local environment so I can "mechanize" the work I do every day managing infrastructure for multiple startups.
Clawd/Molbot/OpenClaw: Reflections and lessons learned
This post isn't meant to be a guide on how to use Clawd, but rather a look at how we're rolling it out at Helmcode to have an AI Agent that helps us with our day-to-day work managing the Cloud infrastructure of multiple startups.