Mitch Ribar

Independent Advisor | AI & Data + CX Strategy | MIT Alum

[Mitch Ribar @reebz]

@trevin /ce-retro looks great, will try tonight. When do you use retro vs. compound now?

[Mitch Ribar @reebz]

@trevin Don’t let the NFT crowd see this 😂😂

[Mitch Ribar @reebz]

@trevin @DavidHruby74 Amazing prompt. I just made that one tiny change to use judgement. I’m in Orca IDE and put it in its own worktree via orchestrate to run via codex.

[Mitch Ribar @reebz]

businesses and customers can both win without switching so we are building https://t.co/VJMPmObBq9

[Alexandr Wang @alexandr_wang]

if this isn’t personal superintelligence i don’t know what is

[Andrew Ng @AndrewYNg]

Good move by @JensenHuang. The Nvidia letter is well written and worth reading. As we saw with the OpenAI-Hugging Face hack, we need open models and harnesses for defense.

Lets stop believing the PR that closed models are safer. - that's just regulatory capture.

[Mitch Ribar @reebz]

@trevin nice - i can finally retire my /prep-to-clear skill

[Mitch Ribar @reebz]

medicine calls evidence without a sufficient counterfactual claim an anecdote (at best) and bans it. Marketing celebrates this as attribution and promotes people for it.

[Mitch Ribar @reebz]

here's a weekend hot take... Most data-driven decision-making is superstition with a dashboard.

[Mitch Ribar @reebz]

decades and decades of work goes into being very very precise about what happened, while remaining ignorant about why. Umbrella sales predict rain with uncanny accuracy and yet handing out umbrellas is a hopeless way to make it rain.

[Mitch Ribar @reebz]

@trevin Even compared to using CC and @orca_build? I love the experience ever since you told me to switch!

[Mitch Ribar @reebz]

yes, thx. want a little further and added scaffolding context, full claude.md entry:

## Project scaffolding

Compound-engineering outputs use a fixed repo layout: `docs/solutions/` (learnings), `docs/plans/` (dated plans), `docs/brainstorms/` (dated explorations), and `todos/NNN-slug.md` with a `status:` field. Reuse this across repos instead of reinventing it.

After a solved, verified problem produces a non-trivial, reusable learning, automatically invoke the `ce-compound` skill, passing `mode:headless` as the skill argument. Only in repositories where `docs/solutions/` already exists.

[Mitch Ribar @reebz]

@trevin quality no argument but I find usage is lower when actively manage context window, i made a /prep-clear since i was clearing so much at 30-45% context

[Claude @claudeai]

Fable 5 is back.

[Mitch Ribar @reebz]

@jeremyphoward And now with this new identity verification, a reasonable claim could be Opus 4.8 is the best from Anthropic an Aussie will ever get. Will push many people to open weights (good thing).

[Mitch Ribar @reebz]

@trevin @kieranklaassen thank you for compound engineering guys

[Mitch Ribar @reebz]

does anyone actually read those long Linkedin posts littered with emojis with excessive line-breaks? genuine question.

[Mitch Ribar @reebz]

@jeremyphoward Yes agree with you

[Mitch Ribar @reebz]

Either Fable/Mythos is more powerful than we know or this US administration continues to punish them for snubbing Pentagon

[Anthropic @AnthropicAI]

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.

The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.

Access to all other Claude models is not affected.

We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.

Read our full statement: https://t.co/bwn0sximKZ