user profile

tosh

183,939karma·27,647submissions·May 4, 2010

about

https://smolenv.com (a smol agent)

https://findableapp.com (SEO toolkit for Google & ChatGPT)

https://kiwilang.com (k-like language and implementation in Zig with support for GPU via Apple MLX)

https://chesscatsapp.com (a fun way to play chess)

https://moreepisodes.com (tv show episodes generated by GPT-4)

https://jamshelf.com (open source Clubhouse)

https://magic.do (early stage fund)

https://lemmings.io (sci-fi themed hackathons (think "zombie apocalypse", "aliens"))

https://applesilicongames.com (game compatibility and game performance on Apple Silicon Macs)

https://devmonthly.com (curated news & input & jobs for software engineers)

https://blossom.io (project tracking for distributed teams)

more from me around the web:

https://twitter.com/__tosh

https://github.com/tosh

https://angel.co/tosh

https://medium.com/@__tosh

https://lobste.rs/u/tosh

https://dribbble.com/tosh

https://linkedin.com/in/tschranz

https://instagram.com/thomas.schranz

https://facebook.com/thomas.schranz

{UX Service Game} Design, Typography, Clojure, Lisp, Python, Tea, Minimalism, Dao, …

[ my public key: https://keybase.io/tosh; my proof: https://keybase.io/tosh/sigs/gBG56O339IbBPh1iaudGL3dgJuX2yONIATYv62xHXdg ]

recent activity (27,647 total)

comment

smol only has 1 tool: sh the system prompt of smol is shorter than the system prompt of Pi smol has no system prompt system prompt of Pi 0.83.0 """ You are an expert coding assistant op…

15d ago·view thread

comment

in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds usefu…

15d ago·view thread

comment

I will look into it more to see if I have configured it wrong but I think the token efficiency hurts cache use as caching only starts at 1024 tokens so for tasks where smol is under or close to 1024 t…

15d ago·view thread

comment

smol is also prefix caching the uncached tokens are also from runs where smol finished a task below 1024 tokens (the minimum amount of tokens needed to activate caching) which is less tokens than othe…

15d ago·view thread

11 pts

Visa to Cut 7% of Workforce(bloomberg.com)

15d ago·discuss

comment

I built an ad-hoc custom comparison framework to inspect system prompts, caching behaviour, tool call outputs, exact api requests and responses and so on I agree fewer tokens is not necessarily better…

15d ago·view thread

comment

ty re --disallowed-tools for coding agents 'shell' is often all you need (just make sure the environment has the necessary tools)

15d ago·view thread

comment

the system prompt still takes up useful space in the context window and steers the model into unnecessary actions and over-thinking patterns

15d ago·view thread

comment

smol is basically this 9 line python agent re-implemented in Go https://news.ycombinator.com/item?id=49006862 I'll have more about it in the next hours/days, you can follow …

15d ago·view thread

comment

the tasks were all simple agentic tasks like creating a checksum of a file, merging csvs and so on, fixing a makefile pipeline with known 'good' outcomes all harnesses could reach the outcom…

15d ago·view thread

comment

I can only recommend to regularly measure how many tokens a harness+model combination uses for a certain task There are huge token efficiency/bloat differences between agents while working on the…

15d ago·view thread

2 pts

Grok: Imagine Video 1.5(twitter.com)

15d ago·discuss

5 pts

Strategic Petroleum Reserve(en.wikipedia.org)

15d ago·discuss

comment

good related read: You and Your Research (Hamming) https://www.paulgraham.com/hamming.html

15d ago·view thread

2 pts

Tamagotchi(en.wikipedia.org)