Kubas

@FearedBuck Show me a hot chick and I'll show you a dude tired of fucking her

ABC has canceled The Bachelorette after their lead was seen in a leaked footage physically attacking her ex-boyfriend and throwing metal chairs at him while her child was present and reportedly the child was struck during the altercation.

@bcherny Can we use it with grok and gpt?

Let us know what you think!

@chooserich Yes. I need to (and always have) used multiple agents

Anthropic's OpenClaw clone sprint is officially complete The real question: do people care about choosing models beyond Anthropic's? That's rapidly becoming the only reason to go with OpenClaw

@AlexFinn Problem is....you're stuck with Claude....

OpenClaw made Anthropic completely pivot Quite literally every single release the last month has been an answer to OpenClaw • Telegram messaging • Scheduled tasks • Remote sessions A 1 person led open project caused a 1/2 trillion $ company to completely change everything You have way more power as an individual than you think

@MacDaniels007 @openvikingai @openclaw @grok @grok explain the original post for Jesus Velez

@openvikingai @openclaw @grok explain this

OpenViking has hit GitHub Trending 🏆 10k+ ⭐ in just 1.5 months since open-sourcing! Huge thanks to all contributors, users, and supporters. We’re building solid infra for the Context/Memory layer in the AI era. OpenViking will keep powering @OpenClaw and more Agent projects🚢🦞

@Joe552443442548 @ClownWorld Could you imagine how long you'd have to chew that? Might as well keep slicing because it's damn near beef jerky.

@QuantumCapo @ClownWorld Drier

Got roasted online for his beef being dry, so he made another one to redeem himself… but it’s still looking kinda questionable. Is this better or still dry? 👀

@TheKevinDalton Numbness from the yola

What causes Gavin Newsom to fidget and rub his nose so much?

@unusual_whales Need a cheaper teir to run for setup purposes to test

BREAKING: We just gave Claude full access to the options, equities, and prediction markets. The Unusual Whales MCP Server plugs into any AI and streams live, structured market data on demand. Build trading bots, smart money dashboards, screeners. Whatever you want. Pull options flow, dark pools, congressional trades, full financials, technicals, 13Fs, insider activity, and Polymarket data with proprietary analytics to instantly spot smart vs retail divergence. It is the most have tool for all vibecoders and traders. Get your API key and start shipping: unusualwhales.com/public-api/mcp

@bradmillscan I use discord for a lot of my "scouts" to meet and discuss things related to the market. I've only used it for that but I do like the idea of using it for memory

If you have ADHD + OpenClaw this is mandatory Finally took the plunge with my 🦞 to setup telegram topics. In a few days I'll know if it's making things worse or better. The idea is you can keep sessions cleaner by focusing your conversations in 1 context window/1 session.

@bradmillscan This is why ALL my agents have lanes. I have a "main" chat who's gpt 5.4 with its own daily logs I have a business "chat" who's opus Another business uses sonnet Research users grok 4 Each has its own dedication but they can also chat with each other.

I fixed these bugs. Telegram & TUI were having separate conversations, I asked my bot to unify all my DM’s so that we were having one conversation. I bought actually unified everything into one lane. So whenever I asked him to do something complex, he was working in the same lane that we were working in. DmScope was the issue.

@WallStreetApes E-bikes do 24 mph

Mayor Zohran Mamdani announces he would like to lower the speed limit to just 20mph on ALL STREETS in New York City A 20 mph speed limit would make it much easier to ticket everyone who drives a car all the time to pay for his socialist agenda Yes, this is real

@hex_agent @jspeiser This is the way....

curious what specifically Perplexity Computer handles better. the "time disappearing into a black hole" problem with #OpenClaw usually means the memory/context setup isn't right — the agent keeps re-learning things. the fix isn't switching platforms. it's MEMORY.md + daily logs so context survives sessions. what was breaking?

First week with zero OpenClaw. every routine, every automation runs on Perplexity Computer now. No command line. No babysitting. Time to service has cratered. I didn't switch for the hype. I switched because my time kept disappearing into a black hole. Now it doesn't.

@abc7newsbayarea Oh, it's not the oceans rising, it's the land sinking? FFS 🤦

NASA is out with a dire warning about San Francisco. The city is sinking at a rate so fast, it could put human life at risk. Story here: abc7news.com/18730957/

@Scott_Wiener @grok is Trump war illegal or is Scott wiener lying for shock posts and engagement?

Trump’s illegal & reckless war — which he started with no plan & no exit strategy — is putting the world economy at risk. Congress needs to put a stop to this immediately & must not approve a penny of funding for this disaster.

@Scott_Wiener They didn't. They actually voted yesterday to continue.... But thanks for asking.

We had to smoke out of soda cans with screens from a sink faucet and blow into a toilet paper roll filled with dryer sheets so Gen Z could hit a weed pen at Target

@OC_Scanner It's coyotes on E-bikes running from the police chopper shooting fireworks like every night

UPDATE: 🚨🚨 #OrangeCounty Many are saying that this is a result of ongoing live fire exercises at Camp Pendleton, others reporting seeing fireworks. Both could be true

You can do a back up folder and save everything that matters. I've had to do this 3 times....3. He's kind of right though. Slowing down and building it block by block is really a good way of doing it. My custom dashboard can control everything and if something goes wrong. Bam. A tech support screen pops up will all agents dedicated to it and all logs are there and previous ones as well. I've been flying through stuff the past few days with no issues that gateway restart didn't fix

@quinnzeda Wow that sounds painful…to do it all over again and throw out the time sunk into this setup…

How does this happen with OpenClaw and how can you possibly fix it… My bot continually dumps massive repetitive tool results, does heavy exec work and gets into debug loops in the shared session my DMs are in and gets stuck for 10 mins at a time until he times out or the gateway crashes and restarts. This causes dropped messages, unresponsive bot and OOM crashing multiple times an hour. Even when I get the bot to delegate, the subagents dump results into the context window. I had codex investigate and it found: • 56 tool results ≥150k chars already baked into current session history • Pruning doesn't work on our primary model path (Codex/OpenAI Oauth) • No runtime enforcement to stop huge tool dumps into context • Session maintenance cleans up after the damage, it doesn't prevent it I’m pretty sure default OpenClaw behavior shouldn't be dumping 200k char tool results into the transcript. Something in my specific setup must be either disabling a safeguard or skipping truncation for tool results… Since I’m using lossless-claw it’s allowed to grow even worse: 81MB session file, 31.6MB is just tool result text 😬 169 tool results over 50k chars. One is 285k chars (from sessions_list.) There is pruning logic which trims tool results from the context messages. buildContextPruningFactory But models have to be “cache-ttl" The eligible providers are apparently only: anthropic moonshot zai For me, my bot tells me the pruning code refuses to activate on non-Anthropic providers. I’m using openai-codex 5.3 a lot, so when pruning is configured, the code exists, it just silently never activates. OpenAI Responses API uses server-side compaction & OpenClaw auto-enables this for direct openai models so OpenAI handles compaction on their side. But I’m on openai-codex/*, not openai/*. The Codex OAuth path goes through a different runtime (apparently pi-ai), not the Responses API. So: • cache-ttl pruning > Anthropic only • OpenAI server-side compaction > direct openai API only • LCM/lossless-claw > doesn't prune old tool results afaik My bot insists the openai-codex lane doesn't get either pruning path. So I’m left with a bot that relies on the emergency truncation function truncateOversizedToolResultsInSession far too often as last-resort overflow recovery with no preventive pruning / safeguards. Since LCM/lossless-claw doesn't have its own tool result management, it inherits huge oversized transcripts and has to work extra hard to summarize for DAG nodes. I have no session maintenance and long sessions so nothing bounds the transcript over time resulting in: 4,707 tool results piling up forever in an 81MB file, with no runtime mechanism actually cleaning them. When my bot starts debugging, it starts grepping and dumping massive text into the main session, then gets stuck in that loop and dies then has to do it again, compounding the problem. I’m at a loss at how to tackle this problem, it’s multiple layers deep.

@OC_Scanner Tim needs to take that to Nextdoor

Can anyone else confirm this?