Trish X

Love learning, sharing, building. ✨

[Trish X @trixai3]

https://t.co/1JlDnEsIz8

[Trish X @trixai3]

Claude usage really adds stress on working with it, and reset feels satisfying.

[Thariq @trq212]

ideal prompting technique is:
- thin prompts
- thick artifacts + context
- thin skills

[Trish X @trixai3]

Building in public ≠ posting your changelog.

Nobody cares that you shipped dark mode. People care why you picked it, what you rejected, and what a user said that changed your mind.

[Trish X @trixai3]

This is how flexible it can be while logging via conversations with your agents. Can just be lazy and say same as yesterday

[Trish X @trixai3]

I got tired of opening food apps every meal, so I tried something else.
I put a tiny GitHub repo on Cursor for iOS. When I eat, I snap a photo, type /log, and the agent estimates calories + protein, appends one line to a JSONL file, and pushes straight to master.
No extra app.
Also we added a foods.jsonl memory. If I correct a portion once (like my small apple is 120g), it remembers. Next time I don’t re-explain the size.
Basically, it’s a personal agent loop:
photo → estimate → append-only log → learn my usual foods → score against my goals.
I’ve been using it for a few days. Still rough on portions. Weirdly good for something that took an afternoon.

[Trish X @trixai3]

@ahmednadar It will flag if a session has been stuck on one tool for over 20 mins.

[Trish X @trixai3]

I run several Claude Code agents at once. I often get lost about which one to switch to, and end up forgetting one of the sessions I opened. Agent-hud sorts every session by who needs me first. So no more clicking through chats to find the stuck one.

[Trish X @trixai3]

@levelsio I've tried similar tracking but using Cursor IOS as portal recently.

[Trish X @trixai3]

Exactly what I need

[Boris Cherny @bcherny]

New in Claude Code: /checkup

Run /checkup to:

1. Clean up unused skills/MCPs/plugins and save context
2. Dedup your local CLAUDE.md against the checked in CLAUDE.md
3. Break up root CLAUDE.md into nested CLAUDE.md's + skills
4. Turn off slow hooks
5. Update your Claude Code to the latest version
6. Enable auto mode by default
7. Pre-approve frequently denied read-only commands

.. And a few other goodies.

/checkup confirms with you before making any changes. Enjoy!

[Deedy @deedydas]

Today’s been an absolutely stacked day for AI news. In case you missed it:

1. GPT 5.6 Sol and Sol Ultra dropping tomorrow. Early reviews say it’s not as smart as Fable but very positive.

2. Grok 4.5 launches from Cursor / SpaceX that claims Opus 4.7 quality at 80tps and $2/M in $6/M out price.

3. Bytedance Seedream 5 Pro launches as an image ~#2 and nearly as good as GPT Image 2 at 4x cheaper cost: $0.045-$0.09/image, specializing in edits and infographics. Easily beats Meta’s Muse Image.

4. GPT-Live launches a full duplex non-turn based voice model which allows interactions while you’re talking seamlessly, a huge upgrade in audio AI for consumer

Coming soon:
1. Seedance 2.5 Pro expected to launch soon (early July) to further extend Bytedance’s lead in SOTA video gen models. Will use Seedream 5 Pro as the frame generator.

2. Gemini 3.5 Pro launching soon (July 17). Google seems to have fallen quite behind frontier and people eagerly await to see what Google can put out here amidst a string of high profile departures.

3. GPT-6 rumored to launch soon (Polymarket spikes at August 14) with a new larger retrain, taking aim at Fable.

[Trish X @trixai3]

I used to tell AI 'add some spacing.' Turns out 'clean' spacing isn't a vibe — it's an 8px scale plus one rule: related things close, unrelated things far.

[Trish X @trixai3]

I've been saying 'make it smoother.' Turns out every motion I wanted already has a precise name — stagger, pop-in, origin-aware, rubber-banding. Learning the words made me 10× better at directing AI to build UI. Naming is control.

[Trish X @trixai3]

Best advice for using Fable

[Simon Willison @simonw]

The most interesting Fable tip I've heard so far is to let the model use its own judgement as much as possible

I told it "For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent" and it seems to be saving a lot of tokens

[Trish X @trixai3]

This sounds really simple to apply. Thanks for sharing! First time to hear simple editor markdown too which sounds cool

[Matt Shumer @mattshumer_]

Here's my in-depth guide to getting the most out of Claude Fable 5, so you can build things as insane as my demos below.

https://t.co/XemOHH7K8E

[Trish X @trixai3]

@khushiirl thx for sharing!

[Trish X @trixai3]

Wrote an article about how it works if anyone interested👉 https://t.co/S7L2M7KkML

[Tech with Mak @techNmak]

OpenWiki is a CLI that writes and maintains documentation for your codebase, built specifically for agents. Run openwiki --init, pick a model, and it generates docs from your repo. A GitHub Action opens a PR once a day to keep them updated. It also appends instructions to your AGENTS[.]md and CLAUDE[.]md so Claude Code or Cursor knows to check the wiki for context.

GitHub Repo: https://t.co/NaNPQK8HI5

[Trish X @trixai3]

https://t.co/4nmtEg4FOc