bespoke agents, with bespoke knowledge bases, bespoke instructions, bespoke tool-sets, and of course, bespoke routing with Jev
make your goon your very own!
It has been interesting to see all the applications of @typesafeai's Jev at @sanity_io.
Like our new internal agent harness which allows anyone in the company to quickly spin up a bespoke agent. Jev is used for the router and has worked pretty well so far!
We (@rostimelk,
Agents have a trust problem.
Today’s models can do most work. What they need is the right boundaries. In traditional software, those were set at build time. With agents, they have to be set and enforced at runtime.
Today we’re introducing Composio Firewall, the runtime boundary
Meet the @typesafeai connector in UiPath Integration Service. 🔗 Bring Jev models into your workflows to make fast, confident decisions at lower cost & latency: uipath.com/blog/product-a…
We put Jev inside the Lightpanda binary and built judge() on top of it. @typesafeai
No more sending a whole page to an LLM just to find out it's a cookie banner.
> Blocked pages, CAPTCHAs, cookie walls, logins, paywalls, error pages, empty searches and pages still loading can
Congrats to TypesafeAI on the Series A!
At the first ever Jevathon, we watched developers build some seriously impressive apps on their new System One model.
Can't wait to see what's next!
who benchmarks the benchmarkers?
a good eval is:
- ephemeral. it snapshots a moment in time and capabilities.
- grounded. it directly measures performance on tasks and data you care about.
- specific. it operates on the desired results and not some proxy of them.
take notes!
Typesafe's CEO @CompleteSkeptic does not trust public benchmarks.
Neither do I, Diogo.
So @p0 and I wrote a blog evaluating 8 decision models on real company training datasets we have personally audited and iterated on.
For what it's worth though, Jev is still on top 👑
(cmd-) f the world
indexing got you down?
can't find your keys?
f that. no really, f that
Jev's got your back
(demo replay for those who missed JevDay!)
our CEO @CompleteSkeptic tells the tale of Dr. Einstein and Mr. Bean
> if AI responds like Einstein 95% of the time and Mr. Bean 5% of the time, how are you going to automate anything with it?
@mattturck talks us through a wild first month of Jev
Crazy launch! Copycats! Massive round! On the one-month anniversary of the launch of Jev, we unpack it all with @CompleteSkeptic, CEO of @typesafeai: what Jev is, how it fixes what's broken in AI, and why the fast-followers are missing the hard part.
00:00 “95% Einstein, 5% Mr.
Jev can cross America navigating by street signs alone
Here's it completing the Cannonball Run from NYC to LA, picking a direction at every turn, given just a destination address and the name of the street it's on
Jev 1.14 is now on OpenRouter.
Per @typesafeai this release is "beautifully boring":
• Everything: a tiny bit better
• Multilingual: the biggest upgrade
• Multimodal: it can see now (experimental)
• Price: unchanged ($0.042/M input, output free)
• Drama: none
openrouter.ai/typesafe/jev-1…
Filtering is the expensive half of a news digest. Every article needs a judgment call, and a judgment call has always meant an LLM call.
Not anymore. $0.00004 per article.
We teamed up with @n8n_io and built a weekday AI brief using @typesafeai's Jev. Now live on n8n blog as part of their Verified Node Spotlight. 🧵
funny, suddenly all of these dynamic designs, structured workflows, and knowledge task solutions are appearing faster and faster, as though it were dramatically easier to automate them.
wonder what happened 🤔
great work @Lovable
142 Followers 838 FollowingSWE (st) | Bootstrapped my own Zero to Freelancing | FOSS/OSS is the way | Neovim, btw | Give me Monster Eng & VimMotions = good(er) code | C/Rust/Zig is him.
7K Followers 2K FollowingAccelerating aligned SI & a flourishing future with neglected approaches & SI R&D. CEO at @aestudiola (SI consulting co puts profits into SI frontier)
1 Followers 15 FollowingWe build production AI systems and help ambitious companies hire exceptional AI engineers. LLMs, agents, retrieval, evals, and MLOps.
107 Followers 2K FollowingType-checking failure only means the program isn’t typable in that system—it may be a real type error or a limitation of the system’s expressiveness/proof power
4 Followers 165 FollowingИИ и разработка — для продолжающих. AI coding, агенты, автоматизация: эксперименты, инструменты, новости и находки. Автор - @deksden
521 Followers 2K Followingbuilding. working hard to keep away from mainstream - human nature, philosophy, tech, food, plants, water (focus on lowest level of Maslow’s hierarchy of needs)
40K Followers 167 FollowingAI infrastructure that developers love 💚
Run inference, sandboxes, batch processing, training, and many other things on Modal
339 Followers 835 FollowingNot really a code rockstar. More of a code singer/songwriter. Improv / literature / internet poisoned woke millenial
He/Him
Mastodon: @[email protected]
157K Followers 79 FollowingSane + 🌶️ takes in an insane AI world... AI capabilities researcher: co-created RLHF/ChatGPT @ @openai now trying to right the wrong 🤭 (ceo @typesafeai)