I've been running OpenClaw as my always-on personal AI assistant for months — Telegram, Discord, WhatsApp, iMessage, Gmail monitoring, calendar, proactive alerts, the works.
Claude Code Channels + Cowork + Computer Use have closed the gap dramatically in just one week. But here's what's still missing for a full replacement:
1. Daemon mode — OpenClaw runs as a headless LaunchAgent 24/7. Claude Desktop needs a GUI session open. Ship a claude-daemon and it's game over.
2. Always-listening channels — OpenClaw receives messages and responds proactively. Claude Channels require an active session with --channels flag. No event-driven "inbox".
3. WhatsApp/Signal — Channels only cover Telegram + Discord. Many of us live on WhatsApp.
4. Group chat participation — Channels are DM-only. Can't monitor and participate in Discord servers or Telegram groups.
5. Multi-provider routing — Sometimes you want GPT for a quick task or Gemini for a specific workload. OpenClaw routes across providers.
The trajectory is clear though. @trq212 and team shipped Dispatch, Channels, and Computer Use in ONE WEEK. At this pace, most of these gaps close within months.
The moment Claude ships a headless background service, the migration becomes real.
I gotta say guys, Claude 4.8 is not looking good. I'm having some very strange problems that were not happening before... maybe it's not the model but the harness (Claude Code) that is broken. But constantly getting "File not Found" when editing a file or "Could not edit file"
@trq212 quite a lot of people facing this error on Opus 4.8. API Error: 400 messages.1.content.81: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified.
Are you guys aware?
Anyone else facing this error with Opus 4.8? API Error: 400 messages.1.content.81: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.
After it happens once,
@toddsaunders I don't know... LLMs are in a state where you can notice the personality differences between models but it's hard to notice anything between increments. I feel like saying anything now is probably placebo kicking in. I'll work longer with it to have a proper opinion.
Here's a comparison with all major model providers (closed and open source)
TLDR:
- The number that actually matters: it fails to flag its own coding mistakes 3.7% of the time, down from 19.7% on Opus 4.7.
- That's ~5x more honest about its own work. Anthropic calls it 4x.
- This is the first release where the pitch isn't "it's smarter," it's "you can trust it with more." It's also the first Claude to score a literal zero on two separate diligence tests.
- Same $5/$25 price as 4.7. Free upgrade.
- Also shipped: dynamic workflows in Claude Code (auto-orchestrated sub-agent swarms that check each other's work), and Anthropic says the restricted Mythos-class model lands in the coming weeks.
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.
@DatGamerDad@TheGameVerse Ohh, I didn't know that! Does it work good enough to be worth me reinstalling it? The graphics were amazing on my GPU though, despite the stutters and slow-downs. I'll investigate how to turn this thing off and see if it works.
@DatGamerDad@TheGameVerse Man, you are the first comment I’ve seen with the same problem I’m having. The game is unplayable for me on any video settings. Stutters and strange slow downs.