almuller3

@Samaytwt Both

Be honest. As a developer, which one is worth it for coding? - GPT-5.5 - Claude Opus 4.7

I applied OC 5.2 to an agent. All went well except my Matrix channel. The fix I applied: •⁠ ⁠installed ⁠ matrix-js-sdk ⁠ into ⁠ /home/sal/.npm-global/lib/node_modules/openclaw ⁠ •⁠ ⁠restarted ⁠ openclaw-agentname •⁠ ⁠verified the import works and the Matrix crash loop stopped

the last 2 version of OpenClaw are not working for me. Agent chat has degraded significantly, and I finally found the culprit. context overflow happens because of excessive tool use, and then openclaw re-injects the last message you sent back to the agent. That's why the agent responds to the same thing over and over. I was having this excessive tool use problem back in March when I was last heavily using OpenClaw ... but it was giving me noisy errors ... now it just silently degrades and fails. The root cause of the problem didn't get fixed ... excessive tool use polluting the session and causing context overflow. The failure mode just changed from a warning message to off-by-1 chat degradation.

@sama Its a great model.

wow y'all love 5.5 we should think of something nice to do to celebrate!

@AlexFinn Damn straight…

Trust nobody's opinion on X (including mine) All I've read for the past 24 hours is how horrible Opus 4.7 is Been using it hardcore for the past day. It is far and away the greatest AI model I've ever used. Don't listen to anybody. They're all bias. Just do your own testing

@elonmusk Yeah only because Chinese evs aren’t allowed in US.

What happened to all the Tesla killers that legacy press and hedge fund short sellers predicted were coming? 🤔

@jaltma Couple of additional crumbs couldnt hurt…

Codex is about to rip 💪

@ClaudeCodeLog I tried on mac, iphone and windows…to ensure not a local issue all works well when not trying to ‘Paste code here if prompted >’

@ClaudeCodeLog I think theres a bug in pasting oauth code

Claude Code 2.1.107 is about to be released #cccnext

@ClaudeCodeLog Does 2.1.107 have a paste issue when attempting to paste the oauth code?

Claude Code 2.1.105 has been released. 2 flag changes, 37 CLI changes, 4 system prompt changes Highlights: • claude-api triggers now include non-Anthropic 'DO NOT TRIGGER' tags to block accidental external calls • Stalled API streams abort after 5 minutes and fall back to non-streaming retries to prevent indefinite hangs Complete details in thread ↓

@bcherny @zeeg Perfection is a high bar…80% great 20% frustration …i like 80% great…i look forward to the closing of the 20% but don’t dwell or let perfection be the enemy of the good… come on people…its life changing and we know it.

@zeeg What bugs are you hitting? Here to help

anthropic being down, rate limits, etc is understandable. huge hardware reqs and insane growth. claude code being bug filled is just a result of people vibe coding slop at anthropic and accepting it as ok. it is not ok you will lose your customers just as fast as you've gained them.

@bcherny Any discussions about an agentic sub… $200 max + ($100 agentic sub )

We want to be intentional in managing our growth to continue to serve our customers sustainably long-term. This change is a step toward that.

Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.

@petergyang @openclaw Wait

Sometimes I send @openclaw a request and it doesn’t respond for a long time because it’s working. Anyone know how to easily cancel the request so it responds? Sending “/cancel” via a chat message doesn’t seem to work

@sama /jaws

I would like a single word for this phrase: "throw it into the maw with every bit of context I can think of".

@openclaw I see it fixes what’s app and matrix what about the echoing?

OpenClaw 2026.3.23 🦞 🧪 DeepSeek provider plugin ☁️ Qwen pay-as-you-go ♻️ OpenRouter auto pricing + Anthropic thinking order 🖥️ Chrome MCP waits for tabs 🔧 Discord/Slack/Matrix + Web UI fixes Upgrade before your agent does it for you. github.com/openclaw/openc…

@ziwenxu_ Yeah just a couple

Openclaw just made a major upgrade, but watch out. Seems like there are a couple of bugs. My Doraemon suggested I wait 24-48 hours for the hotfix.

@Voxyz_ai Well not 100% stable…

openclaw 3.22 stable is out. few things worth digging out of the release notes: clawhub is now a full plugin marketplace. native skill search, install, update. bare plugin installs try clawhub first, npm second. openclaw skills search "memory" openclaw skills install memory-guardian openclaw plugins install clawhub:context7 finding and updating skills just got way less manual. SSH sandboxes. exec, file tools, media reads all run on a remote machine now. remote workspace becomes the sandbox. { agents: { defaults: { sandbox: { mode: "all", backend: "ssh", ssh: { target: "user@your-vps:22", workspaceRoot: "/tmp/openclaw-sandboxes" } } } } } running agents on a VPS and worried about what they can touch? new boundary right here. exa, tavily, firecrawl built in. web search without extra plugins. { tools: { web: { search: { provider: "tavily" } } } } also buried in the notes: every trace of the old names is gone. CLAWDBOT_*, MOLTBOT_*, .moltbot dir, all cleaned out. three name changes, zero leftover ghosts. this release reads like a launch event.

@openclaw Is there an issue with WhatsApp in this upgrade.

OpenClaw 2026.3.22 🦞 🏪 ClawHub plugin marketplace 🤖 MiniMax M2.7, GPT-5.4-mini/nano + per-agent reasoning 💬 /btw side questions 🏖️ OpenShell + SSH sandboxes 🌐 Exa, Tavily, Firecrawl search This release is so big it needs its own table of contents. github.com/openclaw/openc…

@Gianl1974 @Suzierizzo1 Yes

YES OR NO?

@minchoi Both

UPDATE: Sam bent the knee 😂

@JakeCan72 Tool

Trump just cut off Anthropic (Claude AI) Every federal agency. Immediate halt. Here’s what most people are missing: Anthropic had written into its government contract that it could veto how the military uses its own tools. Not Congress. Not the Pentagon. A private company with a San Francisco zip code and a political agenda. Tension arose around surveillance and targeting. Trump saw it clearly: you don’t get to take billions in government contracts and then tell America’s military what it can and cannot do. That’s not a partnership. That’s a leash. For decades, Washington let Silicon Valley write its own rules. This is the first administration willing to say no. Should private AI companies have veto power over America’s national defense? Most people, when they actually think about it, already know the answer.