Stanley Wong

The PRD is the source code. That is the big shift.

[Stanley Wong @swong8]

This is going to shake things up.

[Cline @cline]

We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality:

- GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81)

- Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls

- GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build.

Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!

[Stanley Wong @swong8]

Claude is improving itself!

[Anthropic @AnthropicAI]

Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor.

It’s happening faster than we thought, and the implications deserve greater attention. https://t.co/OVVPJO7VQx

[Stanley Wong @swong8]

SpaceX's S-1 just dropped! https://t.co/4MPXXid4Um

[Stanley Wong @swong8]

@lawrencecchen @tobi This is awesome. Been looking for easy ways of viewing markdown files in cmux.

[Stanley Wong @swong8]

Completely agree. Taiwan has a highly resilient semiconductor ecosystem, much like Silicon Valley has a resilient technology ecosystem. These ecosystems are difficult to replicate because they are complex, networked systems: their strength comes not from any single company or institution, but from the non-linear interactions among suppliers, talent, infrastructure, capital, know-how, and culture.

[Daniel Jeffries @Dan_Jeffries1]

“Taiwan won’t matter in 18 months” is what happens when software people mistake civilization for a SaaS product.

It's one of the most clueless takes I've heard on this platform in months and that's saying something.

Yes, America has semiconductor fabs. Mostly old ones. Really old.

Taiwan has the fabs that matter:

The ones that make every single chip for NVIDIA and Apple and every damn Android and iPhone on Earth and even most of the 1500 or so chips that go in your truck or car.

Without TSMC these companies simply do not exist. Not kind of struggling. I mean "wiped off the freaking face of the Earth and unable to produce a single product" level gone.

As in "worth zero instantly."

Taiwan has:

- Multiple leading-edge giga-fabs

- The *overwhelming* majority of advanced AI chip production

- Dominant advanced packaging capacity

- Dense supplier clustering

- Decades of accumulated yield/process knowledge and the most skilled workforce on Earth to run it all

The US still barely has frontier-scale advanced packaging online. Much of it is literally still under construction and won’t ramp until years from now.

Momos hear “we’re only 1–2 nanometers away” and think semiconductors are just transistor geometry.

No freaking way. Sheer idiocy. The real moat is:

- Yields
- Packaging
- HBM integration
- Substrates
- Tooling
- Tacit manufacturing expertise
- Workforce density
- Supply chain coordination

TSMC is not “a fab.” It is one of the most sophisticated industrial ecosystems ever created by humanity.

And no, a tiny Neuralink surgery robot does not mean America can magically reproduce decades of semiconductor manufacturing concentration in 18 months.

Reality is not a podcast episode.

Taiwan remains strategically critical for years, likely a decade+.

This is like saying:

“We’re 18 months away from replacing the global oil system because we built a nice electric bike.”

[Claude @claudeai]

Effective today, we are:

1) Doubling Claude Code’s 5-hour rate limits for Pro, Max, and Team plans;

2) Removing the peak hours limit reduction on Claude Code for Pro and Max plans; and

3) Substantially raising our API rate limits for Opus models.

[Stanley Wong @swong8]

Woohoo! Now, they need to address stability.... https://t.co/QAWAI8OGFN

[Mitchell Hashimoto @mitchellh]

Ghostty is leaving GitHub. I'm GitHub user 1299, joined Feb 2008. I've visited GitHub almost every single day for over 18 years. It's never been a question for me where I'd put my projects: always GitHub. I'm super sad to say this, but its time to go. https://t.co/DQDemHdytV

[Stanley Wong @swong8]

Anthropic (finally) admits to the recent quality issues we’ve all experienced with Claude Code in a blog post. Reading this, I suspect the Caching Optimization that they pushed on March 26 caused most of our issues as: “Instead of clearing thinking history once, it cleared it on every turn for the rest of the session.” This most certainly caused degraded (Cache misses) & forgetful performance the rest of that session. This issue was resolved on April 10. Read more here. https://t.co/Ued8i4p9wM

[Jesse Genet @jessegenet]

GIANT e-ink display LIVE in my house and actively removing the “mental load” of motherhood 😅

Turns out my household chaos just needed to be tamed by a display my team of @openclaw and @NousResearch Hermes agents manage for me 💅

[Stanley Wong @swong8]

https://t.co/Wv4UvETCzg

[Stanley Wong @swong8]

Another day, another Claude outage... This time CoWork.

[CodedVibes @CodedVibes]

https://t.co/UNgzjjCAHl

[Sigrid Jin 🌈🙏 @realsigridjin]

according to @CodedVibes article,

> claude opus is same model, same intelligence, same instructions but the reasoning depth per response gets cut
> it doesn't forget how to do the work
> it just runs out of budget before finishing it
> sonnet 4.6 actually outscored opus because it doesn't have the same constraints

[Stanley Wong @swong8]

When 4.6 first launched, it was marvelous. Do you think the issues it is having now are tied to its support for 1M context windows, which likely require substantially more backend resources? Along with the sharp increase in usage, that could be creating serious infrastructure pressure. That may help explain why 4.5, with a 200K context window, seems more performant. It is also possible that 4.5 is isolated on separate infrastructure.

[Lawrence Chen @lawrencecchen]

Introducing cmux Claude Code Agent Teams:

`cmux claude-teams --dangerously-skip-permissions`

Teammates/subagents spawn as native cmux pane splits. They stack vertically in a right column and auto-equalize as agents spawn and exit.

`cmux claude-teams` automatically sets CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and shims tmux on PATH with cmux's tmux-compat layer, so you don't need to update your Claude config. All arguments forward to Claude Code, and it works over cmux SSH too.

Out in the latest version of cmux (0.63.x).

[Kyle Mistele 🏴‍☠️ @0xblacklight]

🚨 URGENT 🚨

if you have run npm install / bun install / equivalent in past couple hours

run this - if IoC is found your device is cooked, shut it down and get it to infosec/IT folks asap

[Stanley Wong @swong8]

Claude Code’s source code leaked, so I turned the codebase into a clear architecture diagram. Enjoy

[Chaofan Shou @Fried_rice]

Claude code source code has been leaked via a map file in their npm registry!

Code: https://t.co/jBiMoOzt8G

[Stanley Wong @swong8]

@usenaive @ycombinator naive

[Stanley Wong @swong8]

@muratcan @AndrewYNg Depends. Generally, Context7 MCP is stored globally hence eat up context globally (default). I guess you can install Context7 in a specific sub-agent only, but most people won't do this.