+- Like Ra's Naughty Forum (https://www.likera.com/forum/mybb)
+-- Forum: Fetishes, obsessions, traits, features, peculiarities (https://www.likera.com/forum/mybb/Forum-Fetishes-obsessions-traits-features-peculiarities)
+--- Forum: Kinky Artificial Intelligence (https://www.likera.com/forum/mybb/Forum-Kinky-Artificial-Intelligence)
+--- Thread: Clawdbot (now Moltbot) (and now OpenClaw) (/Thread-Clawdbot-now-Moltbot-and-now-OpenClaw)
Pages:
1
2
RE: Clawdbot (now Moltbot) (and now OpenClaw) - Like Ra - 30 Jan 2026
Errmmm..... It requires models with at least 300B parameters .... Otherwise, the adequacy can not be guaranteed.
That means ... No local uncensored models,
CRITICAL
models.small_params Small models require sandboxing and web tools disabled
Small models (<=300B params) detected:
- ollama/huihui_ai/qwen3-abliterated:8b (8B) @ agents.defaults.model.primary (unsafe; sandbox=off; web=[web_fetch, browser])
Uncontrolled input tools allowed: web_fetch, browser.
Small models are not recommended for untrusted inputs.
Fix: If you must use small models, enable sandboxing for all sessions (agents.defaults.sandbox.mode="all") and disable web_search/web_fetch/browser (tools.deny=["group:web","browser"]).
Local models
Local is doable, but OpenClaw expects large context + strong defenses against prompt injection. Small cards truncate context and leak safety. Aim high: ≥2 maxed-out Mac Studios or equivalent GPU rig (~$30k+). A single 24 GB GPU works only for lighter prompts with higher latency. Use the largest / full-size model variant you can run; aggressively quantized or “small” checkpoints raise prompt-injection risk (see Security).
RE: Clawdbot (now Moltbot) (and now OpenClaw) - Cat73 - 13 Feb 2026
I can almost picture it: a future where AI-controlled gadgets will emerge, followed by AI command-sharing platforms that rely on these gadgets, until... AI-generated prompt attacks... and then an incident occurs.
RE: Clawdbot (now Moltbot) (and now OpenClaw) - dhf7b8g - 15 Feb 2026
(30 Jan 2026, 23:51 )Like Ra Wrote: Errmmm..... It requires models with at least 300B parameters .... Otherwise, the adequacy can not be guaranteed.
That means ... No local uncensored models,
CRITICAL
models.small_params Small models require sandboxing and web tools disabled
Small models (<=300B params) detected:
- ollama/huihui_ai/qwen3-abliterated:8b (8B) @ agents.defaults.model.primary (unsafe; sandbox=off; web=[web_fetch, browser])
Uncontrolled input tools allowed: web_fetch, browser.
Small models are not recommended for untrusted inputs.
Fix: If you must use small models, enable sandboxing for all sessions (agents.defaults.sandbox.mode="all") and disable web_search/web_fetch/browser (tools.deny=["group:web","browser"]).
Local models
Local is doable, but OpenClaw expects large context + strong defenses against prompt injection. Small cards truncate context and leak safety. Aim high: ≥2 maxed-out Mac Studios or equivalent GPU rig (~$30k+). A single 24 GB GPU works only for lighter prompts with higher latency. Use the largest / full-size model variant you can run; aggressively quantized or “small” checkpoints raise prompt-injection risk (see Security).
They have some extremely strange viewpoints on model security and usability. Personally I wouldnt trust any model no matter how big it is to defend against any kind of attack.
Running clawd/molt/claw or whatever it is called now with a smaller (13,24,30) param model shouldnt pose any critical usability issues as long as the model is MCP capable and you arent giving it complex long running tasks. It will take a little more guiding compared to a big model but the same fun 😋 is possible regardless