• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Report

TypeSafe AI's Jev aims to turn natural language into choices software can use

An a16z post shares TypeSafe AI's Diogo Almeida's argument that AI output written for people is hard for software to use. It describes Jev as choosing from a set of options and assigning each a confidence level.

Gary MarcusGM
a16zA1
Ian Maurer 🧬IM
11 Sources, 11d ago, first seen 11d ago

TLDR

In a discussion shared by a16z, TypeSafe AI's Diogo Almeida argues that AI does little real work outside chatbots and coding agents because models generate text for people to read, not output software can consume. The post describes Jev as reading natural language, returning a choice from a set of options and assigning each option a confidence level. It says the approach could help developers build programs that make probabilistic decisions about intent.

Combined views

381K

11 Sources, first seen 11d ago

758 likes96 comments549 saves106 reposts

Combined views

381K

11 Sources, first seen 11d ago

758 likes96 comments549 saves106 reposts

Sentiment

Positive54.7%45.3%Negative

Based on 67 sentiment-bearing replies from 60 accounts across 4 conversations.

Featured Source

Sentiment

Positive54.7%45.3%Negative

Based on 67 sentiment-bearing replies from 60 accounts across 4 conversations.

Related

TypeSafe AI's model launch comes with claims of trillions of tokens served daily

The poster says 29.4% of the Fortune 500 “showed up” and reports a Series A from a16z.

Jev returns with open signups; free credits temporarily disabled for new users

Typesafeai announced on September 27 that Jev was back with increased capacity and open signups. A post quoting the announcement said free credits had been temporarily disabled for new users.

Texas reportedly freezes data center permits after grid queue surges

An a16z essay says ERCOT’s queue hit 474 GW by June, with data centers accounting for about 90%.

11 Sources

a16z@a16zTypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software: Diogo's elevator pitch for Jev is a simple question - where is all the automation? AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output. Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation. TypeSafe's philosophy is "We build prod, not God." 0:50 "Where the f**k is all the automation?" 2:50 Jev vs. Claude Code and Codex 6:55 Jev is a classifier and classifiers are sick 7:40 Chat vs. code: is Jev a slider? 9:00 Diogo: From mathlete to Kaggle to OpenAI 12:20 "We build prod, not God" 15:55 Reliability over demos 16:55 2021 thoughts: RLHF is AGI? 20:45 Optimizing for the wrong use case 21:50 Is the real world too messy to automate? 25:00 Nobody expected the Jev launch 26:35 Three kinds of reliability 28:05 Good at syntax, bad at architecture 30:00 The inverse SaaSpocalypse 33:40 Why coding agents automate so little 36:05 Probabilistic programming returns 38:45 Jev as the UDP-to-TCP layer for AI 40:20 The 5 stages of grief for embedding AI 41:30 Utopia: AI that actually does what you mean YouTube: https://youtu.be/Ut3LOjKNJaE @CompleteSkeptic @typesafeai @bhorowitz @martin_casado11d
Jennifer Li@JenniferHliI'm so much more optimistic about the future. Back to the basics of engineering, but this time with so much power and intelligence. Excited about this path of AI!!11d
Diogo Almeida@CompleteSkepticdid another podcast that want way deeper into my philosophy and love of software! this was super fun11d
Ian Maurer 🧬@imaurerWait until someone tells @GaryMarcus that @CompleteSkeptic said the word "neurosymbolic" on @martin_casado ‘s pod. He was being earnest, and I agree with him. This is how to build useful AI11d
Gary Marcus@GaryMarcusRT @imaurer: Wait until someone tells @GaryMarcus that @CompleteSkeptic said the word "neurosymbolic" on @martin_casado ‘s pod. He was be…11d
Sarah Wang@sarahdingwangRT @JenniferHli: I'm so much more optimistic about the future. Back to the basics of engineering, but this time with so much power and inte…11d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    Diogo AlmeidaJevTypeSafe AI
    a16z

    11 Sources

    a16z@a16zTypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software: Diogo's elevator pitch for Jev is a simple question - where is all the automation? AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output. Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation. TypeSafe's philosophy is "We build prod, not God." 0:50 "Where the f**k is all the automation?" 2:50 Jev vs. Claude Code and Codex 6:55 Jev is a classifier and classifiers are sick 7:40 Chat vs. code: is Jev a slider? 9:00 Diogo: From mathlete to Kaggle to OpenAI 12:20 "We build prod, not God" 15:55 Reliability over demos 16:55 2021 thoughts: RLHF is AGI? 20:45 Optimizing for the wrong use case 21:50 Is the real world too messy to automate? 25:00 Nobody expected the Jev launch 26:35 Three kinds of reliability 28:05 Good at syntax, bad at architecture 30:00 The inverse SaaSpocalypse 33:40 Why coding agents automate so little 36:05 Probabilistic programming returns 38:45 Jev as the UDP-to-TCP layer for AI 40:20 The 5 stages of grief for embedding AI 41:30 Utopia: AI that actually does what you mean YouTube: https://youtu.be/Ut3LOjKNJaE @CompleteSkeptic @typesafeai @bhorowitz @martin_casado11d
    Jennifer Li@JenniferHliI'm so much more optimistic about the future. Back to the basics of engineering, but this time with so much power and intelligence. Excited about this path of AI!!11d
    Diogo Almeida@CompleteSkepticdid another podcast that want way deeper into my philosophy and love of software! this was super fun11d
    Ian Maurer 🧬@imaurerWait until someone tells @GaryMarcus that @CompleteSkeptic said the word "neurosymbolic" on @martin_casado ‘s pod. He was being earnest, and I agree with him. This is how to build useful AI11d
    Gary Marcus@GaryMarcusRT @imaurer: Wait until someone tells @GaryMarcus that @CompleteSkeptic said the word "neurosymbolic" on @martin_casado ‘s pod. He was be…11d
    Sarah Wang@sarahdingwangRT @JenniferHli: I'm so much more optimistic about the future. Back to the basics of engineering, but this time with so much power and inte…11d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet