Diogo Almeida
@CompleteSkeptic
Sane + 🌶️ takes in an insane AI world... AI capabilities researcher: co-created RLHF/ChatGPT @ @openai now trying to right the wrong 🤭 (ceo @typesafeai)
97 Following 147.6K Followers
SO MUCH THIS
I believe that one of jev's greatest benefits to automation will come from resurrecting architecture best practices: state management, encapsulation, abstraction !!!!
and combining them with ML's best practices: measure/evaluate, use calibration/uncertainty
(adding screenshot b/c I don't know how to quote 2 posts 🤦)
Show more
@kieranklaassen some of our biggest prod successes are in this regime - tune-able RAG
Text classification in MotherDuck just got ~50x faster at ~1% of the cost.
prompt_jev() is a SQL function powered by Jev, TypeSafe's new system one model. 100k rows: 40s, $0.50, frontier-LLM accuracy. The LLM took 32 min and $37.
Read on:
Show more
Ashwin benchmarked Jev as a replacement for LLM-based reranking in Ramp's accounting product, and the results are very promising
Jev matches current accuracy on GPT-5.6 Luna, but decreases tail latency by 10x to 300ms at 3x lower cost
We're excited to get this into production for 70k customers as soon as we stop running into rate limits :)
Show more
we got something exciting for you 👀
jev is the top model at 1k-10k context on openrouter!
holy smokes - should this have been our launch video? 🥹
Holy crap.
Rick and Morty just explained Jev AI to me better than any tech demo could.
our special guest is out!
excited to have @CompleteSkeptic join us for Frontiers!
Diogo & @typesafeai have taken over the developer community with Jev, and we're thrilled to see what they have to share at Frontiers!
apply below, closes this week! oct 12-14 fort mason, sf.
Show more
posthog memeing about jev feels like when south park featured chatgpt 🥹
the industry is going full jevons faster than anyone ever thought
at @MetaviewAI, over the weekend we shipped @typesafeai's jev into every agent on metaview.
candidate searches in our sourcing product that took minutes now take seconds. same accuracy, ~10x faster, meaningfully cheaper per search.
but the speedup isn't the interesting part. jev let us treat intelligence like software: break each agent into its smallest semantic units, query each one, set our own thresholds, and fix bugs by adding a question — not by begging in a system prompt.
that's a different way to build, and it's now our baseline. credit to the typesafe team.
optimizing for intelligence per dollar has unintuitive consequences. intuitive to @CompleteSkeptic, of course.
Show more
make it smart n' cheap 👉 put it everywhere 👉 jevon's paradox
Ok so...
JEV just accidentally helped me find backdoors on a family member's wifi network. 🤯
- Brought my laptop to code while visiting.
- Decided to experiment with a JEV-powered classifier for network packets fetched via Wireshark.
While building the tool for fun, JEV's classification caught some serious threats. At first I thought JEV was wrong, but then I got a frontier AI model to validate the findings
...and here we are factory resetting some of their devices and securing their network. 🛠️
@typesafeai's JEV powered cybersecurity is real! Crazy!!
And as always, I'm gonna be open sourcing the network packet analyzer soon.
Show more
is this real? or an exajevration? (sorry)
Jev with Exa is INSANE.
> Jev without websearch confidently gives wrong outputs
> Jev with websearch is literally much more accurate
Try Jev (with Exa websearch) for free 👇
Show more
oops, we're full!
our service is absolutely overflowing right now so we'll have to suspend new signups (old users should be 👌 )
we figured this was the best trade-off to allow our team to sleep 🙏 ty for understanding all
Show more
We have seen such an immense swell of demand that we have to temporarily pause signups for Jev. We need to ensure quality of service for our existing signups, which will continue to function. We are working diligently to ensure open access to Jev for everyone as soon as we can. Thank you.
Show more
super busy but always got time for the devs 💪
Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI
@typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.
Show more
hope props to our platform team! to have one of the biggest launches of all time AND have higher uptime than anthropic is incredible 🥹
For the first time in my life, I witnessed a system built to handle hypothetical high load (normally, it would be called "over-engineered") _actually_ get hit by *crazy* high load, and then endure it successfully.
Show more
AWW I love you guys! (don't read the issue though 🤫)
sharing some notes on typesafe 🤝 coding agents:
we likely will never have time (ever again) to play ourselves, but hope the that the community goes WILD (and makes me look like a naive idiot)
Show more
oh snap. finishing quick used to be a bad thing 💅
Jev is now available to everyone. No waitlist.
Start using it here:
The jevolution
@Mappletons current jev can be called a decision model, but I don't think the shape should be called that
it would be like calling InstructGPT a copywriting model
HINT HINT HINT
the only alternatives to system one I like:
- machine-native model
- large programmatic model
Show more
