hype-free explanation of jev:
jev does not replace gpt / claude
jev is just a *really* smart switch statement
like if 2016 ml classifiers got 2026 levels of intelligence
it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate
* = and by new, i mean rebranded
~~~
it needs a predefined set of options and it will tell you which one to take
it cannot:
- write code
- generate natural language
- reason step by step / show its work
- produce any output you didn't define in advance
- pick from more than ~255 options in one shot
but it can:
- classify, route, score, rank
- give confidence
- pick the right branch, tool, model, or sub-agent
- judge / verify / guardrail an llm's output
- label tons and tons of rows
~~~
i'd imagine a lot of workflows that look like:
llm proposes options → jev decides → code executes
and i see this fitting *really* well with code mode and mcp
~~~
implying this will lead to agi seems incredibly far fetched to me, but i don't want to discount the types of applications that this will make possible
O mundo foi construído por pessoas que não eram mais inteligentes que você. Você também pode criar coisas que outras pessoas vão usar.
Steve Jobs lembrando que a gente pode mudar o que parece pronto.
100% editado com Astra, guiado pelos meus comentários.
@demaritech
@masahirochaen Apple Park is the perfect Astra demo. I used the same idea—turning direction into a finished artifact—to edit this Steve Jobs video: https://t.co/inWJU2n4LW
O mundo foi construído por pessoas que não eram mais inteligentes que você. Você também pode criar coisas que outras pessoas vão usar.
Steve Jobs lembrando que a gente pode mudar o que parece pronto.
100% editado com Astra, guiado pelos meus comentários.
@demaritech
O mundo foi construído por pessoas que não eram mais inteligentes que você. Você também pode criar coisas que outras pessoas vão usar.
Steve Jobs lembrando que a gente pode mudar o que parece pronto.
100% editado com Astra, guiado pelos meus comentários.
@demaritech
@thayto_dev sinto que pra tarefas no geral o GPT vai muito bem.
usar o Luna no GPT Work é ouro
mas talvez pra umas tarefas mais pesadas de código o fable funcione melhor
@nikhilbhima Basically had the same result today: 7GB → 58GB free after a Codex-assisted audit. Dev caches, node_modules and build output were the real culprits. Such a good agent use case.
@TorontoTP 256GB Macs really do turn storage management into a recurring subscription to anxiety 😅 Keeping around 50GB free is now part of my maintenance routine.
@jjpcodes This is the nightmare scenario I was trying to avoid. Mine reached 97% full; node_modules, build output and agent tooling had quietly piled up. Auditing before deleting was the key.
@pawelkarniej Local agents can turn a laptop into compute + cache + workspace graveyard very quickly. I recovered 51GB by separating active workspaces from regenerable artifacts.
@glnarayanan@WhatsApp@HiTw93@ChatGPT WhatsApp was one of the largest app-data buckets on mine too. Definitely something to clean through the app rather than manually deleting its databases.