Harness and model are trained together, others are less effective, e.g. by not having an apply_patch function.
@steipete
-
Code reliability improves with fewer bugs as codebase scales
By
–
reliability, far fewer bugs esp as the codebase grows.
-
Anthropic subscription issues? Try alternative AI model providers
By
–
Anthropic subscription? Try another model provider or auth method to rule out an issue on their end.
-
CLI for Coding vs Apps for Knowledge Work
By
–
cli for coding, app for knowledge work (slack email cal files notion linear obsidian twitter discord…)
-
OpenClaw OpenShell Sandbox Architecture Technical Debate
By
–
I think it's the wrong approach, you want OpenClaw use OpenShell as sandbox, not the other way around.
-
Microsoft Teams improvements spark collaboration tool innovation race
By
–
Microsoft already shipped some amazing MS Teams improvements, the door is open for others too! Slack folks should join the party in a few days, talking with the team there.
-
OpenClaw maintainer welcomes Telegram bot API streaming fixes
By
–
Talked with @durov and Telegram folks offered uncomplicated help, welcome @izhukov as new OpenClaw maintainer! First action point is to figure out why enabling the bot streaming API sometimes causes message dupes. This will make Telegram support so good!
-
Discrawl 0.2.0 Shipped: Faster Discord Sync for Community Analytics
By
–
Shipped 0.2.0 of discrawl, syncs much faster now. I use it every day to understand what the biggest pain points are in the OpenClaw Discord.
-
Knowledge Cutoff Will Persist in All Future AI Models
By
–
Knowledge cutoff is a thing. It will be in every model in the future, forever. So we good 🙂