# Claude Haiku 4.5, Skills, Veo 3.1, and nanochat

> Week of 13 Oct 2025: Claude Haiku 4.5, Agent Skills, Veo 3.1, Karpathy's nanochat, PaddleOCR-VL, a Gemma-based cancer lead.

Published 13 Oct 2026. Coverage: 13 Oct 2025 to 19 Oct 2025. By Ali Asif.

## Items

1. **Claude Haiku 4.5** (Anthropic, Frontier): A small model that Anthropic says matches Sonnet 4 on coding at about a third of the cost and twice the speed. [Primary source](https://www.anthropic.com/news/claude-haiku-4-5)
2. **Equipping agents with Agent Skills** (Anthropic, Agents and coding): Skills are folders of instructions and scripts that Claude loads only when a task needs them. [Primary source](https://www.anthropic.com/news/skills)
3. **Veo 3.1** (Google, Image, video, world): Richer native audio, reference images and scene extension arrive in the Flow filmmaking tool and the Gemini API. [Primary source](https://blog.google/technology/ai/veo-updates-flow/)
4. **nanochat** (Andrej Karpathy, Science): A small codebase that trains and serves a ChatGPT-style model from scratch for around a hundred dollars of compute. [Primary source](https://github.com/karpathy/nanochat)
5. **PaddleOCR-VL** (Baidu PaddlePaddle, Open weights): A compact vision-language model for document parsing with tables, formulas and many languages. [Primary source](https://huggingface.co/PaddlePaddle/PaddleOCR-VL)
6. **Cell2Sentence-Scale and a new cancer hypothesis** (Google DeepMind and Yale, Science): A Gemma-based model proposed a drug combination that lab experiments then partly confirmed. [Primary source](https://blog.google/technology/ai/google-gemma-ai-cancer-therapy-discovery/)

Anthropic spent the week shipping the pieces of a working agent stack, and I found the smaller ones more interesting than the model.

## Haiku 4.5 and Skills

Claude Haiku 4.5 arrived on Wednesday. Anthropic says it reaches roughly the coding level of Sonnet 4 at about a third of the cost and twice the speed. The reason that matters is arithmetic. If you run many agents all day, the cheap model does the bulk of the work and the expensive one is called only for judgment. I tier my own agent work that way, and a better small model shifts the line.

The next day came Agent Skills. A skill is a folder holding instructions, scripts and resources, and Claude reads it only when the task calls for it. That keeps the main context lean while letting you give the agent deep, specific know-how. I've been doing something like this by hand for months, with written procedures for each recurring job, so seeing it become a product feature is validating. It also means a company's operating knowledge can be written once and reused across tools.

## Video and building from scratch

Google released Veo 3.1 with better native audio, support for reference images, and the ability to extend scenes, available in Flow and the Gemini API. For short-form content work the reference-image support is the practical gain, since it keeps characters consistent between shots.

Andrej Karpathy published nanochat, a compact codebase that goes from raw text to a working chat model for about a hundred dollars of compute. I don't plan to train a model, but I learn the most about a tool by looking at the smallest honest version of it.

## Documents and science

Baidu's PaddleOCR-VL is a small document-parsing model for tables, formulas and many languages. Anyone drowning in scanned PDFs should test it. Google and Yale published work where a Gemma-based model proposed a cancer-related drug combination, and lab tests partly supported it. That is a real example of a model producing a testable hypothesis.

## What I'd watch next

OpenAI is rumored to be building its own browser. If it ships, the contest moves from chatbots to who owns the page you're looking at.

## My take

Skills is the quiet release that fits how I already work. I keep a folder of procedures for each recurring job, from RFQ intake to price-catalog refreshes. Having the model load a procedure only when it applies is the difference between a long prompt I babysit and an operating manual that scales.

## Sources

- https://www.anthropic.com/news/claude-haiku-4-5
- https://www.anthropic.com/news/skills
- https://blog.google/technology/ai/veo-updates-flow/
- https://github.com/karpathy/nanochat
- https://huggingface.co/PaddlePaddle/PaddleOCR-VL
- https://blog.google/technology/ai/google-gemma-ai-cancer-therapy-discovery/

Canonical: https://heyaliasif.com/ai/2025-10-13-week-in-ai