digital icebreakers bananadoh slippery boxes spacetraders data browser More...
software by Stafford Williams

software by Stafford Williams

blog more

links more

    OpenAI to buy Windsurf for $3 billion.

    openai, ai, moat • 2025-05-06 • 8:16pm

    Firefox integrated AI chatbots into a new sidebar within the browser but the integration doesn’t appear to have access to the page the browser is currently on 🤦. It appears to just be an iframe/tab to the provider’s normal web interface.

    ai, firefox • 2025-05-06 • 12:10pm

    ComfyUI is integrating external API models and demonstrate gpt-image-1 integrated with a ComfyUI workflow. The catch for now is you can’t supply your own API key/endpoint and rather require a ComfyUI account that you load with credits. Pricing reflects OpenAI list price.

    comfy-ui, ai, image-gen • 2025-05-01 • 9:00am

    Chain-of-Vibes by Pete Hodgson sums up nicely the approach I take to leverage the power of agentic AI workflows while sidestepping the limitations. Treat the tools “like weirdly knowledgeable, hyper-productive junior engineers”, give enough context but otherwise limit their output. Importantly, review the outcome of each small task and make a decision:

    A) Accept and commit
    B) Prompt to adjust
    C) Manually fix up
    D) Revert and re-prompt

    The last item is an important one that’s often overlooked - throwing away the result and fixing your prompt is often more time efficient, especially when learning how to prompt.

    blog, ai, prompting, code-assist • 2025-04-29 • 11:28am • LinkedIn icon

    Prompting has deceptive simplicity. It seems like it should be straight forward but for me it’s required a lot of practice to get better results. Aidan Boyd’s post How I talk to AI has a good summary of how he thinks about prompting before doing so.

    ai, prompting, blogs • 2025-04-28 • 2:31pm • LinkedIn icon

    Google releases Gemini 2.5 Flash allowing developers to switch between reasoning/non-reasoning at the API level.

    $0.15/1mil tokens input
    $0.60/1mil tokens output (no reasoning)
    $3.50/1mil tokens output (reasoning)

    gemini, ai, google, model • 2025-04-20 • 7:42pm

    OpenAI has released o3 and o4-mini, their most powerful reasoning models. These models outperform their predecessors while delivering answers in under a minute. OpenAI also launched Codex CLI, an open-source terminal tool, with a $1 million fund to support related projects.

    o3 $10/mil tokens input, $40/mil tokens output
    o4-mini $1.1/mil tokens input, $4.4/mil tokens output

    openai, ai, model • 2025-04-17 • 6:58pm

    GPT 4.1 is announced as 3x developer-centric model releases available specifically via API. An internal instruction following eval was used to improve the model’s ability to follow instructions. Context size is 1m tokens. Pricing appears competitive if the new models have similar performance to Gemini/Sonnet:

    gpt-4.1 $2/mil tokens input, $8/mil tokens output
    gpt-4.1-mini $0.4/mil tokens input, $1.60/mil tokens output
    gpt-4.1-nano $0.1/mil tokens input, $0.4/mil tokens output

    GPT 4.5 will be deprecated over API in a few months

    ai, openai, model • 2025-04-15 • 11:30am

    The mui folks mentioned a year ago they’d focus on extending base-ui and extracting it to it’s own repo. This has now been done and I note the docs have moved to base-ui.com and see an improved emphasis on accessibility.

    From the creators of Radix, Material UI, and Floating UI, Base UI is an unstyled React component library for building accessible user interfaces. Our focus is on accessibility, performance, and developer experience. Our goal is to provide a complete set of open-source UI components, with a delightful developer experience, in a sustainable way.

    Tailwind integration looks to just work as opposed to the steps needed to enable it in mui.

    mui, base-ui • 2025-04-08 • 6:39pm

devlog more

notes more

digital icebreakers bananadoh slippery boxes spacetraders data browser