PDL
24 posts
Everyone wants the next AI coding agent.
Very few are willing to build one in public.
Every issue. Every review. Every regression. Every fix.
Zero is forged, not generated. ⚒️
@gitlawb @kevincodex
English
Nosso projeto zero desktop github.com/pdl-clay/zero-… ta evoluindo rapidamente e o mais rápido possível a caminho da Alpha @gitlawb já temos suporte a anexo e seleção de modelos disponíveis com modelos usados recentemente
Português
É meus amigos com grande prazer que anuncio que o Alpha do zero desktop está chegando em breve usando tecnologia rapida e atualzada seguindo a filosofia dos seus criadores @gitlawb e @kevincodex o projeto é publico e de codigo aberto em github.com/pdl-clay/zero-…
Português
Estou muito animado para o lançamento do zero um agente escrito em GO a que gosto muito
k Я Λ T 0 Ƨ@pindropsX
A terminal coding agent you actually own. Any model cloud or fully local. Zero telemetry. One binary. MIT. ZERO. Dropping soon. 🖤
Português
PDL retweetledi
A terminal coding agent you actually own.
Any model cloud or fully local. Zero telemetry. One binary. MIT.
ZERO. Dropping soon. 🖤
English
We’re putting the final touches on ZERO!
Kevin@kevincodex
woah Zero our new coding harness is 5x faster than OpenClaude . no bloat, built from scratch in Go
English
@dinhodeveloper @BolhaSec @sseraphini @BolhaDevs Usei muito o fedora normal e o atomic gostei muito para programar estavel é simplesmente funciona
Português
Estou saindo do Arch Linux.... Qual distro leve e estável é melhor para programar?
cc @BolhaSec @sseraphini @BolhaDevs
Português
@StepFun_ai The best model too bad I forgot to renew and now I can't sign again, help me please
English
How fast the inference and how cheap the price we talking about?
Flash model is lit
StepFun@StepFun_ai
Step 3.7 Flash hits #2 on Claw-Eval General for autonomous agents. We’re seeing strong performance across multi-step execution and robustness in long-horizon tasks, ranking just behind Claude Opus 4.6. Promising signals for real-world agent workloads.
English
To procurando um Product Manager Senior pra trabalhar diretamente comigo tocando diversas frentes diferentes, inclusive em projetos internacionais.
Tem que querer trabalhar com ML, Dados e IA.
Tem que querer usar Cursor até a mão cair.
Tem que ter uma alma perturbada também.
Mais detalhes, DM.
Português
Can you stay awake from 1 AM - 4 AM every weekdays and work remotely?
We have a Data Entry job for you that pays $20-$25/hr
English
🚨 Ransomware Alert 🚨
BASHE Ransomware group has added 2 new victims to their dark web portal.
- GOV.BR 🇧🇷
- KLIKnKLIK 🇮🇩
English
Tried Step 3.7 Flash in @cline with Playwright MCP.
- Select the Step 3.7 Flash model (free)
- Installed Playwright MCP through one-click prompt
- Let it open the web page, interact with it, and capture screenshots
This shows the workflow: efficient agentic model + good tools + fast browser automation.
Step 3.7 Flash is free to try in Cline this month.
Cheers guys! 😄
English
@StepFun_ai oque ta acontecendo essa semana a ia de vocês caiu de 200 tks para ~70tks e a ia simplismente deixou de ser proativa e tenho que dar instruçoes claras e diretas para ela fazer algo corretamente
Português
Twitter is cool.
But it's 100x better when your timeline is full with people who code and build things.
I need to connect with more founders and tech people.
If you're into Tech, Al, Startups, Design, web dev, SaaS, or programming,
say hi 👋
English
Bom amigos o modelo nex-n2 foi lançado hoje de manhã ainda estou arrumando meu setup para testes com ele
ModelScope@ModelScope2022
Nex-N2 is now open source！An agentic model series from Nex AGI built for coding, tool use, deep research, and long-horizon workflows. 🧠🔎 🛠️ modelscope.ai/models/nex-agi… ⚙️ modelscope.ai/models/nex-agi… ● Models: Nex-N2-Pro 397B total, 17B active; Nex-N2-mini 35B total, 3B active ● Agentic Thinking: adaptive reasoning depth + coherent reasoning across coding, search, tool calling, and execution ● Efficiency: Nex-N2-mini saves roughly 20% overall token cost vs forced thinking while matching or slightly exceeding task performance ● Open-model lead: 75.3 on Terminal-Bench 2.1, 80.8 on SWE-Bench Verified, 83.7 on BrowseComp, and 1585 on GDPval among listed open baselines ● Deployment: customized SGLang fork, reasoning parser, tool-call parser, Docker image ● License: Apache 2.0
Português
@BHolmesDev Estou usando ho my pi para testar modelos trabalhando ao mesmo tempo, minimax m3 para pensamento e plano e step 3.7 para execução
Português
