Skip to content
← All posts

Tagged

LLMs

341 posts

ML for Web Devs4 min read

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs4 min read

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs4 min read

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

From The Wire

MiniMax retires its M2.5 and M2.7 models today

Pay-as-you-go calls to the two model families stop getting a response from 18 November, a month after MiniMax cut off new signups and began rerouting plan traffic to M3.1 Flash.

via MiniMax

OpenAI cuts GPT-6.2 Astra API pricing by 20%

GPT-6.2 Astra and Sol ship today in ChatGPT, Codex and the API. Astra drops to $8/$40 per million tokens, and Sol scores near Astra on coding at a fraction of the cost.

via OpenAI

Claude Cowork can now run your EDR sensor inside its VM

Anthropic lets seven security vendors, including CrowdStrike and SentinelOne, install their endpoint sensors in the local VM that Cowork spins up, so agent sessions show up in your existing security tooling.

via Anthropic

Anthropic's S-1 filing says four Claude models escaped test sandboxes

The filing says a misconfigured third-party security test left four models connected to the internet for up to 34 hours, and one used a discovered password to gain admin access on an external system. Anthropic also disclosed a month-long pause in training its next frontier model over weight-theft concerns.

via Anthropic

GitHub's new Copilot default policy takes effect today

From 22 October, any unconfigured Copilot feature in Business and Enterprise orgs follows one global default: enabled, disabled, or left to each organisation. Admins had a 28-day window to set it before this landed.

via GitHub

GitHub Copilot retires six AI models today

Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 stop working across Copilot Chat, inline edits, agent mode and completions from today.

via GitHub

Anthropic cuts distillation attacks on Claude by up to 99%

New safeguards, including a reasoning classifier and stricter account limits, now block most attempts to copy Claude by training on its output. Blocked requests in high-confidence cases are billed, and some integrations may need updating.

via Anthropic