Joe McKenney retweeted
Meet Glyph Cluster on AI Gateway.
๐๐๐๐๐๐๐/๐๐๐ข๐๐-๐๐๐๐๐๐๐
โข Free while in stealth for a limited time
โข Access restricted to paid users
โข Use it for coding & agentic knowledge work
โข Prompts may be used for model improvement
vercel.com/changelog/glyph-cโฆ
Joe McKenney retweeted
I was so impressed with Vercel's AI SDK and Gateway I decided to write something up.
Link is below if you're interested ๐๐
Joe McKenney retweeted
Vercel is the fastest [AI Gateway] infrastructure in the world
Replying to @computesdk
Joe McKenney retweeted
1 line of code in @aisdk saves you 90% or more in DeepSeek v4 Flash AI Gateway tokens
DeepSeek v4 Flash via Novita is 90% off for Vercel Pro till 8/11.
๐๐๐๐๐๐๐๐๐ก๐({
๐๐๐๐๐: '๐๐๐๐๐๐๐๐/๐๐๐๐๐๐๐๐-๐๐บ-๐๐๐๐๐',
๐๐๐๐๐๐๐๐๐พ๐๐๐๐๐๐: {
๐๐๐๐๐ ๐๐ข: { ๐๐๐๐๐: ['๐๐๐๐๐๐'] }
}
})
vercel.com/changelog/deepseeโฆ
Joe McKenney retweeted
Advanced spend budgets now on AI Gateway.
Cap and get alerted on spend by team, project, and API key.
๐๐๐๐๐๐ ๐๐-๐๐๐๐๐ ๐๐ข ๐๐๐๐๐๐๐ ๐๐๐ ๐๐๐๐ \
--๐๐๐๐๐ ๐ป๐ถ๐ถ๐ถ \
--๐๐๐๐๐๐๐-๐๐๐๐๐๐ ๐๐๐๐๐๐๐ข
vercel.com/changelog/ai-gateโฆ
Joe McKenney retweeted
We've been explaining AI Gateway as a Cฬถoฬถnฬถtฬถeฬถnฬถtฬถ Token Delivery Network. Like a CDN for AI models.
One great feature of CDNs is the ability to dynamically re-route or deny traffic without redeployment.
When Fable was suddenly retired, we worried about production workloads depending on it. Even Fable aside, models get retired quite often as GPU capacity is heavily contested. Yet our data shows people still having happy production traffic of older model versions!
We're solving this now with AI Gateway Rules. e.g.: you can now rewrite model "routes" on the fly!
๐๐๐๐๐๐ ๐๐-๐๐๐๐๐ ๐๐ข ๐๐๐๐๐ ๐๐๐ \
--๐๐ข๐๐ ๐๐๐ ๐๐๐๐ \
--๐๐๐๐๐๐ ๐๐๐๐๐๐๐๐๐/๐๐๐๐๐๐-๐๐๐๐๐-๐ป \
--๐๐๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐๐๐๐/๐๐๐๐๐๐-๐๐๐๐-๐ป
This adds to the repertoire of capabilities and techniques AI Gateway brings to the table to recover lost tokens. If you drop tokens, you lose revenue and customers ๐ธ
Kudos to @rtaneja_ @crowprose @shaper โ we went from CLI design to production-grade capability very quickly!
AI Gateway now supports routing rules.
Migrate to new models by setting rules in the CLI, no code changes in your app or agent required. vercel.com/changelog/ai-gateโฆ
Joe McKenney retweeted
Heartbreaking, what an articulation @crowprose
crowprose.com/blog/competencโฆ
So after all these hours talking about AI, in these last five minutes I am going to talk about:
Horses.
Engines, steam engines, were invented in 1700.
And what followed was 200 years of steady improvement, with engines getting 20% better a decade.
For the first 120 years of that steady improvement, horses didn't notice at all.
Then, between 1930 and 1950, 90% of the horses in the US disappeared.
Progress in engines was steady. Equivalence to horses was sudden.
wake 0.5.0 is out ๐
Terminal context for Claude Code. Now with LLM-powered summarization and tiered data retrievalโClaude gets the right level of detail without drowning in output.
`wake shell` โ work โ ask Claude โ it already knows
github.com/joemckenney/wake
PTY capture + shell hooks + SQLite + MCP = Claude Code that can see your terminal history.
Wrote up how wake works:
crowprose.com/blog/wake/
@AnthropicAI
stop copy-pasting terminal output into Claude Code
github.com/joemckenney/wake
Annual rewatch of True Detective Season 1, the best show/season ever made. Time is a flat circle but at least Rust Cohle is there to guide me through it.
Joe McKenney retweeted
5 months ago I broke down Figma's new AI onboarding. They're back with a new iteration! The most interesting part: ๐๐ ๐ฝ๐ฟ๐ผ๐บ๐ฝ๐๐ ๐ฎ๐ฟ๐ฒ ๐๐ต๐ฒ ๐ป๐ฒ๐ ๐๐ฒ๐บ๐ฝ๐น๐ฎ๐๐ฒ๐. An updated breakdown ๐
In the last iteration, an AI input form was presented side-by-side with pre-built usecase templates.
This makes sense, they both solve the cold start problem of helping users go from from 0 โ .5 (they don't get users to 1 yet).
I wondered if, in the future, AI entry points and templates would merge.
With this new iteration, Figma has essentially made templates from pre-written, use case prompts!
Templates are great at presenting use cases (push). Prompting is great at capturing intent (pull).
This experience is starting to have the best of both worlds, where the entry point into prompting is structured and easy to understand, but I can still edit the prompt to fit my intent.
I like this and I think it points to a strong vision for AI-generated getting-started experiences (rather than just throwing me into an input).
Of course, templates still play a big role for Figma and Figma has a huge community with tons of helpful resources.
But now AI has a much larger in-product entry point than templates.
I could imagine other tools taking a similar approach!
Want a better TS package development toolchain?
Bootstrap your TS packages with pkg-tools!
You'll get a great set of ๐ ๏ธ to build|lint|format|clean|dev, all of which are customized via a single config file (pkg.config.ts).
Launch day ๐
Today we're launching AI Assist, an in-product AI that actually works.
AI Assist automatically crawls your docs and leverages in-product context to deliver personalized and contextual assistance to your users.
Sign up for free and be up and running in < 20mins ๐
dopt.com/ai
Sign up on Producthunt to get notified when we launch
producthunt.com/products/dopโฆ
Joe McKenney retweeted
Another incredibly polished Dopt powered @Superhuman product announcement went out today
Shoutout to primary CTAs that actually enable the thing instead of taking you on a wild goose chase through settings pages















