software by Stafford Williams
Follow @staff0rdblog more
- 2025-03-16 Embrace Vibe Coding, Know Its Limits
- 2025-03-09 You Might Not Need an AI Framework
- 2025-03-03 Understanding AI-assisted Coding Workflows
- 2025-01-29 Running DeepSeek R1 Locally
- 2025-01-12 LLM Agent Assisted Coding
- 2024-10-14 Comparing Netlify and Azure Static Web Apps
- 2024-04-16 Evaluating ngrok
notes more
- 2025-03-03 [javascript, timezones, vitest] timezones
- 2025-01-14 [bookmarklet, chrome] add text to clipboard
- 2024-12-11 [javascript, timezones] datetime libraries
- 2024-11-18 [macos] links
- 2024-03-13 [azure-b2c] limits
- 2024-03-11 [azure-b2c] phone mfa - microsoft samples
- 2024-03-06 [http] testing
devlog more
- 2024-05-29 [spacetraders-v2] v2.14 - more data browser
- 2024-05-16 [spacetraders-v2] v2.13 - data browser
- 2024-05-04 [spacetraders-v2] v2.12 - reset 2024-04-09
- 2024-04-21 [spacetraders-v2] v2.11 - monitoring markets
- 2024-04-18 [spacetraders-v2] v2.10 - trading contracts
- 2024-03-31 [spacetraders-v2] v2.9 - improved waypoint monitoring
- 2024-03-28 [spacetraders-v2] v2.8 - over supply
links more
Claude now has web search but it’s only
available now in feature preview for all paid Claude users in the United States. Support for users on our free plan and more countries is coming soon.
OpenAI release o1-pro and it costs $150 per million token input and $600 per million token output.
Currently, it’s only available to select developers — those who’ve spent at least $5 on OpenAI API services
A rules-based pattern is emerging for helping agentic workflows produce better results. Examples include GreatScottyMac’s RooFlow and, Geoff Huntley’s specs and stdlib approaches.
Brendan Humphrey on Vibe Coding, aligns with my own thinking on vibe coding:
…these tools must be carefully supervised by skilled engineers, particularly for production tasks. Engineers need to guide, assess, correct, and ultimately own the output as if they had written every line themselves.
Smashing Create PR with vibe coding output amounts to an attack on the PR process:
Generating vast amounts of code from single prompts effectively DoS attacks reviewers, overwhelming their capacity for meaningful assessment
But there is still some value:
Currently we see one narrow use case where vibe coding is exciting: spikes, proofs of concept, and prototypes. These are always throwaway code. LLM-assisted generation offers enormous value in rapidly testing and validating ideas with implementations we will ultimately discard.
Eugene Yan’s blog - Senior Applied Scientist at Amazon
Simon Willison’s blog - ai researcher, independent open source developer, co-creator of the Django Web Framework
Hamel Husain’s blog - independent AI consultant
Evalite - a vitest-based eval runner by Matt Pocock.
Introducing GPT-4.5 - hallucinations down, accuracy up, non-reasoning. Rolling out to pro + api. Doesn’t look like anyone will be coding with it any time soon with this type of api pricing:
Input: $75.00 / 1M tokens
Cached input: $37.50 / 1M tokens
Output: $150.00 / 1M tokens
And then in a tweet from sama:
this isn’t a reasoning model and won’t crush benchmarks. it’s a different kind of intelligence and there’s a magic to it i haven’t felt before. really excited for people to try it!