Matt Freindlich

Market enthusiast, data junkie & Raider Nation fanatic. Aspiring 80's golfer. In an open relationship with @msexcel.

[rari @0xwhrrari]

Holy f*ck, Opus 5.5 replaced After Effects

It's f*cking insane…

Drop the PDF below into Opus 5.5 and see what it makes

Then read the full guide on motion design in the article below ↓

[Masa’s Son @masayoshisson]

AI predictions for next 6-9 months

-> Anthropic/ OAI fail to ban OSS in the US
-> Anthropic/ OAI continue to innovate product but stall on fundamental tech breakthroughs
-> SOTA Gemini 4 launches at 10x lower cost
-> Elon open sources Grok
-> Anthropic/ OAI ARR growth stalls as enterprises move from tokenmaxxing to rational token consumption/ OSS
-> slow realization in public markets that AI may not replace human labor in next 1-3 years/ has not had a fundamental tech breakthrough in over a year/ lacks ROI/ AI hyper and lab spend not durable
-> moonboy VCs/ hedge funds/ softbank continue to fund Anthropic/ OAI equity raises in private markets as public markets for them are now fully closed
-> CXMT, YMTC announce capacity expansions significantly above market expectations
-> hypers deliver good q326 results on first look but fail to show meaningful AI ROI, guide to "significant capex expansion in fy27"
-> broad realization in public markets the AI dream we got sold on is not anywhere close to realization
-> 10yr hits >5%
-> hyper bonds reprice >10%, CDS hit 3x current levels, and AI credit market dries up as market realizes GPU ABF was not a good idea
-> hyper equities reprice 30-50% lower
-> ORCL falls below $30 as rumors of bailout make the round
-> market realizes memory is cyclical and LTAs won't hold
-> 50% of korean traders get wiped within a week
-> hypers cut fy27 capex
-> semis reprice >80% lower
-> fed cuts >150bps to avoid recession

[Suraj Sharma @suraj_sharma14]

7 plugins to install before you touch Claude Code again.

All free. Over 800K GitHub stars between them.

1.) Superpowers (298K stars)
Makes Claude brainstorm, plan and test before it writes a single line of code.
https://t.co/cpyd6nJkfS

2.) Everything Claude Code (278K stars)
71 agents, 300+ skills, memory and a security scanner, all from one install.
https://t.co/IJQtabmpr9

3.) UI UX Pro Max (135K stars)
Gives Claude real design sense, so your apps stop looking AI-generated.
https://t.co/mgzWqGfb58

4.) Claude-Mem (100K stars)
Saves what Claude did in each session, so you don't have to re-explain your project every morning.
https://t.co/KRQYP6bLip

5.) wshobson/agents (40K stars)
A whole marketplace of specialist agents for backend, DevOps, docs and testing.
https://t.co/rINPZPeqv0

6.) Trail of Bits Skills (7.5K stars)
Security auditing skills from one of the best-known security firms.
https://t.co/znwIraGCZE

7.) Playwright Skill (3K stars)
Claude opens a real browser, clicks through your app and tests it on its own.
https://t.co/jqhFJJdn75

Don't install all 7 at once. Start with the one that fixes your biggest pain.

[cat.png @1920web1080]

holy f*ck, SpaceXAI just listed 56 jobs you can hand to Grok Bot, and each one installs in one click

sales, marketing, support, recruiting, finance, product, engineering, life admin

this is the full list from the Grok Bot use cases page, one-line job for each

apartment scout books tours the minute a listing goes live

security questionnaire filler logs into the vendor portal and drafts every field

bug reproduction clicks the same path in staging and drops a repro pack with screenshots

here you open the page, pick a job and hit add

how to use the list:
1. scroll through all 56
2. stop on the job you hate doing
3. add that one first

save this, check the use cases below ⭣

[AI_Explorer @ai_explorer25]

Best 15 accounts to follow in AI:

@karpathy = LLMs king
@steipete = built openclaw
@gregisenberg = startup ideas king
@rileybrown= vibecode king
@jackfriks = solo apps king
@levelsio= startups king
@marclou = startups king
@EXM7777 = AI ops + systems king
@eptwts = AI money twitter king
@ai_explorer25= AI queen
@godofprompt =prompt king
@vasuman = AI agents king
@AmirMushich = AI ads king
@0xROAS = AI UGCs king
@egeberkina = AI images king

Follow them all and learn.

[Dan McAteer @daniel_mac8]

A Claude Coder ran Claude 945 times to measure what practices save on tokens vs. which do not.

Most useful:

- /clear
- /compact
- Move instructions from CLAUDE.md to a skill

Least useful:

- High effort (vs. Medium)
- Haiku 5.5 (vs. Sonnet 5.5)
- Unused rules

[Computer @AskPerplexity]

REA (Reverse Engineer Anything) by @morluto is now a skill in Computer.

Ask Computer to reverse-engineer an app and it inspects how the app works without its source code, then builds a working version.

Tasks that use /reverse-engineer are free through October 31, up to 10,000 credits per user.

Here are 5 apps Computer made with it, available to try for a limited time:

1) Figma: Design with layers and auto-layout, plus sign-in, cross-device sync, and multiplayer editing. Try it: https://t.co/FGGTblkCWY

[Florence @flxrnc]

The After Effects era is ending, and Opus 5.5 is the reason

this is unreal…

Drop the PDF below into Opus 5.5, you’ll thank me later.

Then save the article, it’s the only Opus 5.5 motion design playbook you’ll need.

[CyrilXBT @cyrilXBT]

i can't comprehend why people run claude code on default settings

one settings change and every model gets its own job:

→ opus plans every task and advises when stuck
→ sonnet 5.5 writes the actual code
→ haiku handles every file search
→ a critic agent tries to break your diff before you merge

Opus thinks. The cheap models grind.

paste this into claude code 👇

Add this to ~/.claude/settings.json. Keep every hook, permission and plugin I already have. Then create the two agent files below and show me the diff.

```json
{
"model": "opusplan",
"advisorModel": "opus",
"effortLevel": "medium",
"modelSettings": {
"claude-opus-5-5": { "effortLevel": "high" },
"claude-sonnet-5-5": { "effortLevel": "medium" }
},
"env": {
"CLAUDE_CODE_SUBAGENT_MODEL": "haiku"
}
}
```

~/.claude/agents/scout.md
```
---
name: scout
description: finds code fast. returns file paths and line numbers only.
model: haiku
tools: Read, Grep, Glob
---
Locate exactly what was asked. Return file:line. No fixes. No opinions.
```

~/.claude/agents/critic.md
```
---
name: critic
description: reviews a diff or plan before any task is called done
model: opus
tools: Read, Grep, Bash
---
Assume this is broken. Find how it fails. One line per issue, worst first.
```

[Asteri @Asteri_eth]

this list is straight up f*cking gold for motion design

20 open-source GitHub repos to run your own motion design studio with Opus 5.5

one pick per layer: agent skills, animation, 3D, assets, sound and export

01 Remotion → write React, get real editable video
https://t.co/2MnpZQrLlw

02 Remotion Skills → official video recipes for Claude Code
https://t.co/nz3anwkCYf

03 Motion Canvas → code explainers and animated diagrams in TypeScript
https://t.co/rWQTitvtlP

04 Motion AI Kit → feed Claude Code the Motion docs and best practices
https://t.co/FlFx1A7NhH

05 Motion → smooth layout transitions and gestures in live UI
https://t.co/1orZ6aMbHM

06 GSAP → frame-precise timelines for text and SVG
https://t.co/HhwPzpCe1Y

07 Anime.js → draw SVG paths, split text, move UI pieces
https://t.co/fFxawh6xPV

08 GSAP Skills → teach Claude Code clean timelines and React teardown
https://t.co/HdSTwCBEXF

09 Rive Web → vector animations that react to app state
https://t.co/5VTFCZi5YK

10 dotLottie Web → play, pause and steer Lottie files
https://t.co/IDX2Ulm0y8

11 Three.js → 3D shots with real cameras and lights
https://t.co/KQBagkuShd

12 React Three Fiber → write 3D scenes as React components
https://t.co/efNx10EPLX

13 Drei → ready-made cameras, 3D text and controls
https://t.co/9j6H7yy6w6

14 React Three Rapier → physics: collisions, joints, rigid bodies
https://t.co/IeWy9Z5OxI

15 React Postprocessing → bloom, depth of field and the final polish
https://t.co/cEE83wAzIq

16 SVGO → strip the junk out of SVGs before you animate them
https://t.co/qCv95NeftJ

17 Satori → JSX in, SVG title cards out
https://t.co/WozmVoiIPe

18 Howler.js → sound effects, fades and volume for web demos
https://t.co/9AVsnL9zLr

19 Mediabunny → encode and convert video right in the browser
https://t.co/bX2k89OrQS

20 FFmpeg → final encode, resize and file checks
https://t.co/bfqyckTvNL

the workflow:

brief → typography → motion → scene → sound → render → review → ship

bookmark this + the article below shows how to wire up your own motion studio

[Josh Barzon @JoshuaBarzon]

6,000 years of world history on a single timeline. Zoom in. You could spend 30 minutes exploring this.

[mirku @mirku21]

https://t.co/PaAzxlyrsH

[mirku @mirku21]

THIS IS A PURE F*CKING GOLDMINE

Anthropic just shared the sharpest trick for Claude Code

The idea: let Opus 5.5 write the plan as a script, and swarm the new Haiku 5.5 in parallel

Huge sweeps with zero Opus burn: the script holds the loop and Opus only sees the final diff

You just launch Claude Code like this:

claude --model opus --effort ultracode

here's the split:

→ Opus 5.5 turns your objective into an executable workflow script
→ Haiku 5.5 swarms every file in parallel at 340 tok/s to extract candidates
→ Sonnet 5.5 patches each fix and cross-checks findings in its own isolated copy
→ you stop burning Opus context on a hundred agent transcripts

Opus only shows up at three moments:

→ authoring the workflow script before the run
→ reading verified findings after the swarm finishes
→ signing off before anything ships to git

Opus plans · Haiku scans · Sonnet ships

JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split

the full tree
> Opus 5.5 runs the main session and writes workflow.js
> pipeline() fans out the new Haiku 5.5 to audit every file
> parallel() schema validators drop false positives in V8
> Sonnet 5.5 patches each fix in an isolated worktree
> verify cross-checks all diffs before reporting
> Opus 5.5 reads only what survived verification
> JEV routes micro-forks in milliseconds

paste the tree and this prompt into Claude Code ↓

"Rebuild my Claude Code setup around this tree:
1. Run the main session on Opus 5.5 with ultracode on
2. In every workflow, run read-only scan stages on the new Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy
3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress
4. Route fast deterministic forks (tool choice, path selection, retries) through JEV
Show me every change as a diff first, no edits until I say go"

↳ https://t.co/PcTdH7dyjb

save it, it'll come in handy

[Andrew M. Dai @AndrewDai]

Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that.

Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.

[Claude @claudeai]

Six projects from the last few weeks that caught our attention:

A wildfire analysis prototype that maps the fire’s spread over time and tracks hot spots, made with Opus 5.5.

[MAZE @mazemoore]

🤣😂🤪

[AI Guides @free_ai_guides]

BREAKING NEWS 🚨: Grok Bot can now read your X bookmarks, and turn the 2,000 posts you never reread into a second brain.

Connect your X account and use these 7 prompts:

[Autism Capital 🧩 @AutismCapital]

NEW: Highlight reel of all the stunts performed at the Tesla Roadster event. INSANE 🔥🔥🔥

[Parker Washington @CPW11_]

Chop Wood, Carry Water. #DUUUVAL

[Unicus @UnicusResearch]

🚩Here is a news story that got less coverage than $NVDA.

A Miami investment firm, 777 Partners, is accused of pledging the same collateral to two lenders and borrowing against assets it never owned. Its biggest lender was an insurance group.

Regulators woke up (after the fact) and said 30% of its invested assets sat in junk-rated private credit and unrated loans, against a 10% cap.

It gets way worse. 🧵