Chris Vaillancourt

Full stack shenanigans

[Chris Vaillancourt @christopher__v]

@lydiahallie but you do pay extra if you keep using claude -p like we do today? It's the same subscription price with reduced capability

[Chris Vaillancourt @christopher__v]

LOL this is a simplification? yet another usage quota to juggle.

[Noah Zweben @noahzweben]

We're launching a huge SDK credit simplification on June 15:
* Agent SDK/-p draws from a new bucket instead of your interactive limits (which stay exactly the same)
* Every plan comes with $20-$200 of monthly SDK credits
* You can use 3P tools like T3/OC with these credits

[Matt Pocock @mattpocockuk]

This is the clarity we've been crying out for.

But it's a poisoned chalice. This is a 10X cut to claude -p disguised as a monthly bonus.

Anthropic is discouraging any kind of programmatic usage. And that's fine - no subsidy lasts forever.

But it's time to try Codex.

[Adam Wathan @adamwathan]

Claude Code not supporting `.agents/` for skills and stuff is annoyingly hostile 🫠

[Chris Vaillancourt @christopher__v]

Related reports showing the same pattern:
https://t.co/a7gGri7J1k (Feb 28)
https://t.co/x6kpH0HHm9 (Apr 17)
https://t.co/GKTLBw0Ujr (Apr 17)
https://t.co/6EMlKZluLM (Apr 20)

[Chris Vaillancourt @christopher__v]

@bcherny Please help: https://t.co/4YFKYKfngF: 5h session reset jumped ~4h forward near the boundary, no reset fired.

Not isolated. 5 reports Feb→now across 5h and 7d windows; mine's the first 5h-scoped one. Looks like mid-cycle resets_at recomputation.

[Chris Vaillancourt @christopher__v]

why does this not use my plan's usage limits?

[ClaudeDevs @ClaudeDevs]

New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud.

Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, data migrations, etc.

Pro and Max users get 3 free reviews through 5/5.

[Chris Vaillancourt @christopher__v]

For real, please help me understand why new features don’t tap into my existing usage budget? @TheAmolAvasare

[Leo @planetleoo]

You need to fix your delivery, comms, approach, all of it. Consumers don’t really give af about an A/B test. Ik you said consumers will hear it from yall and not a screenshot, but they DID hear it from a screenshot first and that prompted you to respond.

To consumers simply looking to signup and then they see this tweet, you look like you fleece people for a quick buck.

If your products are stating to be in the hands of more every day users, you need to speak their language

[Scott Tolinski @stolinski]

Over engineered react patterns have poisoned how AI writes Svelte and other framework code. Like yo, it doesn't need to be that complicated.

[Glauber Costa @glcst]

What if we could run Postgres as a single file, and take advantage of the best SQLite has to offer?

Today I am announcing pg-micro, a crazy experiment I've been undertaking to make this happen.

pg-micro is different than other approaches because it is fully local, and expected to be fast: there is no concurrency limitation and no statement translation.

Here's how it works: we use the actual postgres parser to parse the statement, but compile that to the Turso AST. The Turso AST is then compiled do bytecode, and from there everything executes natively, as it'd do in SQLite. This makes it a perfect target to run in any environment.

There is traditionally a mismatch between Postgres and SQLite in terms of functionality. But @tursodatabase has been hard at work to close this gap: things like MVCC and a rich, strict type system are present in Turso. There are PRs for things like lateral joins, etc. This means that the gap can be closed until it theoretically reaches zero.

What you could do with it? Just imagine for example a primitive like Durable Objects by @Cloudflare, but with a postgres interface? Or imagine you could use the same pattern of local databases for agents that SQLite gives you, totally ephemeral and free, but with a Postgres interface? Or even that you could execute remote postgres in platforms like @vercel but with the unmatched density of the Turso Cloud?

Expect lots not to work at this point. But as usual, this is done in the full spirit of OSS, so PRs welcome!

To get started: npx pg-micro

[Chris Vaillancourt @christopher__v]

A lot hinges on what openAI does with uv. Before the astral acquisition, I'd argue that uv makes python a lot nicer for agents than TypeScript but now ¯\_(ツ)_/¯

https://t.co/sfos5QeEVE

[Justin Schroeder @jpschroeder]

Seems obvious that TypeScript - not python - is turning into the Lingua Franca of agents.

[Cline @cline]

Introducing Cline Kanban: A standalone app for CLI-agnostic multi-agent orchestration. Claude and Codex compatible.

npm i -g cline

Tasks run in worktrees, click to review diffs, & link cards together to create dependency chains that complete large amounts of work autonomously.

[Wei Dai @_weidai]

The state of Claude vs. Codex, in two tweets.

[Chris Vaillancourt @christopher__v]

But will a single prompt use your entire usage quota?

[Yuchen Jin @Yuchenj_UW]

Anthropic’s new model, Capybara:

“Compared to Claude Opus 4.6, Capybara achieves dramatically higher scores in software coding, academic reasoning, and cybersecurity.”

According to Dario's previous interview, it might be a 10T-parameter model that cost $10 billion to train.

[Dhruval @dhruvalgolakiya]

Maybe claude should just remove $20/m plan at this point?

I don't see any reason why anyone will or be able to use that plan, 4-5 prompts and you are out of limit

[Chris Vaillancourt @christopher__v]

This morning, 2 sessions used 72% of my "current session" usage quota. I have a premium seat in my team plan. The first session used 154k tokens and the second used 152.7k tokens. I'm absolutely baffled and immediately switched to codex :/

We need a visible usage multiplier

[Thariq @trq212]

To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged.

During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.

[Chris Vaillancourt @christopher__v]

@mikal_bridges @Suns NO 😤

[Chris Vaillancourt @christopher__v]

@NBA fix your refs. They’re broken.