… I linked to mine in the blog post, and included the exact prompts I used to build it https://
github-spark-docs.simonwillison.net
@simonw
-
GitHub Docs: Building AI Tools with Exact Prompts
By
–
-
Unsolved AI Problem: Three Years of Limited Progress
By
–
It's possibly the hardest problem in AI – people have been trying to solve that for nearly three years and have made hardly any progress on it at all I've been following it pretty closely!
-
Claude Token Counter Tool Overview and Usage
By
–
About 9,950 according to pasting it into https://
tools.simonwillison.net/claude-token-c
ounter
… -
Bulk PDF Data Extraction for Large Scale Applications
By
–
Anyone who is doing bulk operations for things like structured data extraction against large numbers of PDFs… or anyone with a app that serves thousands of users
-
Anthropic 10x Tier 2 Rate Limit: 450K Tokens Per Minute
By
–
Anthropic just 10x the rate limit tier 2 and up Tier 2 is the one you get when you've bought at least $40 of credits – previous rate limit for Sonnet 4 was 40,000 tokens per minute, the new limit is 450,000 tokens per minute! (Tier 2 request-per-minute has stayed at 1,000)
-
Spark System Prompt Teaches Web Design Principles
By
–
I've read a lot of system prompts and the Spark one is genuinely one of the most interesting I've seen yet – I learned a bunch of things about web design including typography and color theory as a side-effect of reading through the prompt!
-
Monetization incentives drive controversial AI discourse online
By
–
That's sadly true – the way monetization here works provides a huge financial incentive to post controversial takes that get a ton of reactions
-
Feature requests for future iterations of Spark
By
–
I included a few of my own feature requests for future iterations of Spark https://
simonwillison.net/2025/Jul/24/gi
thub-spark/#spark-features-i-d-love-to-see-next
… -
FAANG Layoffs Impact Senior Engineer Job Market Recovery
By
–
Right – the job market still hasn't recovered from FAANG companies laying off 100,000s of senior engineers over the past few years
-
Spark API Endpoints for GPT-4o LLM Calls Without Proxying
By
–
Not in its current state, no – thankfully you don't need to proxy API keys for LLM calls with Spark because they run an API endpoint for you (just for gpt-4o and gpt-4o-mini at the moment though)