Would love a plan from OpenAI, Anthropic, Google that includes API credits. I'd be more willing to pay a premium for the higher tiers if they gave some space for experimentation outside of first-party apps. It seems OpenAI is doing a bit of this with their codex-cli would love

Task Master - github.com/eyaltoledano/c… is a gamechanger. I'd argue that there's as much value in it focusing _you_ the developer as there is in focusing AI agents to breakdown and execute work

I've been working in claude code so much this last week that I looked at my sink full of dishes and my first thought was "I wish I could construct a task for that"

I was absolutely locked in on OpenAI's models, using it for personal and professional use cases -- my favorite feature being voice mode + memories. Lately I've been using Claude for almost everything - mostly because Claude Code is fantastic and the max plan lets me use Opus in

Twilio's pricing is extortionate. Are there alternatives out there that don't suck?

i've flip flopped between models quite a bit over the last couple of years. I've kind of settled on: * openai (4o+o3) - life stuff * claude (opus+sonnet) - code generation * perplexity - rapid prd-generation and feature research I wonder if we start to see these models start to

Gemini is great but the product fragmentation is straight up disorienting. I get why vertex exists, but separating the Gemini AI Ultra plan from Code Assist Enterprise is confusing. Big miss

I've played a lot with v0, but I'm actually really enjoying stitch.withgoogle.com v0 has a ton of integrations, which is great to get from 0 to 1 but sometimes I just want to brainstorm some screens.

I've pretty much moved on from Claude Code at this point. Aug-Sep was such a rollercoaster of availability and quality that I just can't trust it any more. I've been evaluating a ton of other solutions and made my workflow more flexible, the tooling lock-in just evaporated.