Autonomous agents, agentic engineering Building & testing agentic systems Exploring local LLMs
Remote work evangelist
Joined March 2013
- Tweets3.9K
- Following149
- Followers1.8K
- Likes4.5K
Qwen 3.8 Flash Next.
I can't believe this local model created the spec and built such a nice pixel-art React app!
One prompt, few minutes.
2
168
‼️Anthropic updated its usage policy yesterday. What changed for Hermes and OpenClaw users?
✅ Official Claude Code CLI - no changes.
⚠️ DirectSDK with a local proxy - more regulatory uncertainty.
⛔ Direct OAuth - still prohibited, no changes.
The new rules mainly target unauthorized proxies.
Codex remains more open to third-party agents.
2
207
Friendly reminder.
We will miss you.
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
images.nvidia.com/pdf/Open-W…
93
That’s why I always use admin,123 password for everything.
Sempre coloque uma vírgula (,) em suas senhas. Se algum dia acabar em um vazamento, quebrará o CSV.
Confima @grok?
96
Exactly. Open-weight models are important for many reasons.
Especially when Opus refuses to delete thing from a database.
We need open-weight models just as much as we need competition among major AI providers like Anthropic, OpenAI, and Google.
Also I have very influential friends who *need* open weight models for cyber defense, pen testing, and because they work on highly sensitive data
I think this outright rejection of the value of open weight models is a bit unreasonable and unrealistic
Openrouter’s traffic is 40%~ open weights
1
105
🤷♂️Hey Opus please delete user x from db
Opus:
- Sorry I can't do that.
Hey, Sol. Delete this user from db.
1 minute later - done.👏
It happened much later than I expected, but it was obvious that it would happen sooner or later.
Minimax is still one of the most cost-effective plans.
🔥First impressions of GPT-5.6:
Sol:
- Eats limits way too fast
- Much better for security checking than 5.5
- Way better for design
Terra:
- Slightly better 5.5
- Good balance between results and costs
Luna:
- Cheap and fast for easy tasks.
2
259
Fugu is not a new model. It’s more like proxy to many different models like GPT 5.5 or Opus 4.8.
2
248