
My Codex Agents Were Posting to Slack as Me
On the morning of November 13 I found a message in a Slack thread with my AI team, posted under my...
Tag archive

On the morning of November 13 I found a message in a Slack thread with my AI team, posted under my...

Using GenAI to sound like literally anyone but you. Everyone knows the trick. You paste three of...

A coding agent got a ticket: a customer with exactly 100 points can't redeem the 100-point reward. It...

A 36-layer model just ran 96 layers per token, and nobody changed its weights. That's what a looped...

Work out if a local LLM fits and how fast it can run before downloading it: weights, KV cache, the Mac GPU memory limit, bandwidth ceilings, and MoE models.
Alibaba's Qwen team dropped a new flagship today: Qwen4-Max, built on a brand-new Qwen4 architecture...

By the Cuelark Team. Every release, price and date below comes from the vendor's own blog, docs or...
How to catch prompt and model regressions in CI with a golden set, pass-rate thresholds, and a response cache, using plain pytest.

I built a tiny AI email assistant and sent it one email with a hidden line of text. Instead of...
When learning to code with AI tools, the path of least resistance is copy-pasting. A student types a...
If you have tried to feed a Substack newsletter into an LLM or a RAG pipeline, you have probably hit...
If you've ever wired an LLM agent or a text-to-SQL script up to a Postgres database, you know the...