CRO ideation workshop at Canon, London
How to generate new, meaningful ideas?
- Speak to real human customers
- Gather real humans from different parts of biz
- Outline clear opportunity, based on what real humans are trying to get done
Ban any "use AI" easy cop out ideas.
“Most CRO test screenshots are bullshit” 🎯
@andrewjfaris great pod w/ Mars Men head of ecom
He lists the most common issues, but this quote nails it:
“Doing CRO is easy, doing CRO the right way is hard”
Sol Medium -> sweet spot intelligence vs cost per task
Fable -> if you want absolute highest intelligence, cost secondary
Sol High -> near-top intelligence at far better value
Sonnet 5 -> meh
Opus 4.8 -> overpriced vs Kimi K3, basically an expensive Sol High 👇
One of my first CRO clients was 16 years old at the time.
That was 15 years ago. He did well, could’ve retired by now but still grinding nights and weekends.
I love that founder energy.
Why design tasks burn so many Claude tokens and what to do about it.
“make it bigger” / “center it” etc reload the entire convo
Every mcp loads its definitions in every message, even if not used
Select only the specific Figma component
and other tips
yummy-design-sprint.notion.s…
Tip: use Gemini CLI with @obsdmd instead of Claude
Claude + Obsidian having a moment on X
… but Claude tokens are precious
You get ample free requests in Gemini CLI, if you want 3.1 pro it’s pennies via the api.
Bro we can see AI wrote your tweet
Why TF would I bother reading it if you can’t be bothered writing it?
I speak to AI all day, I come here for human voice
What I’m trying to figure out: where do open (read cheap!) models fit in?
- GLM-5 for planning, refactoring
- MiMo-V2-Flash, Devstral 2 highly praised for coding and popular on Openrouter
You don’t need frontier models for everything.
I’ve used Opus 4.6 and GPT 5.4 on a mix of projects since release, and want to break down where I think they uniquely excel. It’s more nuanced than you’d think!
Rigor of code - GPT 5.4. It goes the distance validating its work without asking. Opus needs explicit instruction to do this, and even then, it misses more edge cases.
Clarity of code - Opus 4.6. Claude is a better communicator, which carries into the code. Variable names are clearer and less mechanical, which improves reviewability. This is very important since code review is the bottleneck for most engineering teams. It also adds the right amount of doc comments. GPT simply never comments or explains its work; it’s like working with an obtuse engineer that wants the solution to speak for itself. Sometimes it does, other times not.
Similarly, rigor of plans goes to GPT 5.4, while clarity of plans goes to Opus 4.6. An interesting point though: GPT performs better talking through a strategy without a plan, while Opus needs planning mode to put in any rigor. I find myself forgetting plan mode altogether using GPT 5.4.
Quality of research - toss-up. Opus spends longer researching with web search, but GPT spends longer studying the existing codebase. You may think codebase research matters more, but researching how others solve the same problem can be just as important. Maybe more important for greenfield.
Quality of conversation - Opus 4.6. It’s just better to talk to, which matters using these things everyday. GPT 5.4 was clearly trained to challenge the user more, which results in a tendency to *always* say you are wrong. I’ve had bizarre interactions where GPT claims something is “not quite right,” the restates exactly what we’ve decided on in the last turn. On a personal level, it’s annoying. On a practical level, it makes iteration on a plan slower. THAT SAID, it takes sufficient pushing for Opus to challenge your thinking in this way. Simply say “I’m impartial” and ask questions to avoid that, as you would a person.
Overall winner - Opus to make it work, GPT to make it good. I don’t have a good system of when to switch tools, but on average, I prefer Opus early on and GPT for optimization and discussing architectural decisions. Opus is also better for any design related tasks (but state management in frontend apps is better handled by GPT).