Alex Marples

@cherry_mx_reds 🤞

give gpt 5.4 another chance 🦀✨

@budapp Watching thr game, having a Bud.

Introducing Bud. The first AI Human Emulator. Bud has a full computer with storage, compute, and memory to build and code, sms and telegram to communicate, a full browser to use, can create/store/edit files, connect and use your tools, learn custom skills, work fully autonomously, and complete any task end to end just like a human. Text the number below or try free at bud [dot] app. Comment for 100k free credits.

@MindsAI_Jack Yep; as assistant, researcher, sounding board.

Is anyone who was super excited for OpenClaw still using it and finding it beneficial?

@thsottiaux Computer use for windows; avoid delays for UK releases; eagerness/proactivity for openclaw.

Hello builders. What are we getting wrong with Codex, what can we improve?

@steipete @LoopOnChain 👀

@LoopOnChain Yeah there's a bunch more work that's in the pipeline, this will change this week.

.@steipete thoughts on this? (or any other openclaw superusers) Seems to be the prevailing sentiment. Is this a skill issue or is Opus simply better than 5.4 (maybe 5.5 catches up?) I've struggled to get 5.4 to perform even close to where I was at with Opus 4.6, i've spent a LOT of time with it Seems like using codex as the default harness is most helpful but only gets me 60% of the way there Curious you and the other Clawtributors findings after a few weeks post Anthropageddon

@jordymaui Yep, 🙋 interested.

going to be building a community > vibe coders > openclaw users > hermes, claude code, codex users > curious AI folk who want to learn if any of these sound like you reply below, i’ll invite you early (not an engagement farm - excited for this!)

Dear @StravaSupport. Suggest your product people quickly look at the process for Facebook login email switching. It doesn't work. You're going to lose a lot of users!

@thsottiaux Windows wen?

Codex just got a lot more powerful. Computer use, in-app browser, image generation and editing, 90+ new plugins to connect to everything, multi-terminal, SSH into devboxes, thread automations, rich document editing. Learns from experience and proactively suggestions work. And a ton more.

@aakashgupta Adjusted for socio-economic factors? Clear click-bate; you got me.

Tennis players live 9.7 years longer than sedentary people. Not 9.7 months. 9.7 years. Nearly a decade. The Copenhagen City Heart Study tracked 8,577 people for 25 years and ranked every sport by how much life it adds. Badminton: 6.2 years. Soccer: 4.7. Cycling: 3.7. Swimming: 3.4. Jogging: 3.2. Tennis almost triples jogging. A separate study of 80,000 adults found racket sports cut all-cause mortality by 47% and cardiovascular death by 56%. Swimming hit 41%. Aerobics hit 36%. The question is why racket sports destroy everything else. Three mechanisms stack on top of each other. First, the physical demands. A tennis rally requires explosive sprints, lateral cuts, and sustained aerobic output. You're training fast-twitch and slow-twitch muscle fibers simultaneously. Most cardio only trains one system. Second, the cognitive load. You're reading spin, predicting angles, adjusting position, and executing motor patterns in real-time. Your brain is solving spatial puzzles at 80+ mph. That hand-eye coordination and strategic processing builds neural connections that protect against cognitive decline. Third, and this is the one researchers keep coming back to: you literally cannot play alone. Every racket sport requires another person on the other side of the net. That forced social interaction triggers neurochemical benefits that solitary exercise cannot replicate. Strong social connection alone increases your chance of longevity by 50%. Jogging is you and your thoughts. Tennis is you, a strategic opponent, and a community. Dr. Daniel Amen is right. The data is overwhelming. If you want the single highest-ROI activity for a longer life, pick up a racket.

@hthieblot Hearing

pitch me your company in 1 word.

I've definitely spent more time optimising @openclaw than getting value from him these past few days. He's gone super-brittle.

@signulll This has been the vision sold to us by White Goods OEMs since the advent of IoT. Might finally become reality!

i want a refrigerator with a camera agent inside that uses ai to keep track of what is there & how much, then orders it whenever you’re running low lol.

@cherry_mx_reds Having the WORST time with active memory, typically 27 second latency on balanced/recent. Issue is somewhere in runEmbeddedPiAgent as opposed to the model call. Any fixes in this drop🙏?

👋 A few useful OpenClaw 2026.4.14 changes that didn’t make the main tweet 🦞 ✨ GPT-5.4 runs are less likely to stall or waste a turn, with better recovery for empty/reasoning-only replies plus support for `gpt-5.4-pro` and `xhigh` on `github-copilot/gpt-5.4` 🌐 Local/Ollama setups are less annoying to run, with real usage reporting, correct timeout handling, restored embeddings, and fewer false “unknown model” tool failures 🧵 Telegram forum chats are easier to follow, because agents can keep using human topic names instead of opaque thread IDs, even after restart 🛡️ Admin surfaces are harder to misuse, with safer gateway config patching, stricter Slack/Teams allowlist enforcement, and broader browser/CDP SSRF protection 📦 Subagents are less likely to get mysteriously stuck, because npm builds now ship the runtime file they were missing Docs: OpenAI / Codex docs.openclaw.ai/providers/open… Ollama docs.openclaw.ai/providers/olla… Local models docs.openclaw.ai/gateway/local-… Telegram docs.openclaw.ai/channels/teleg…

@BoxminingMartin @openclaw Assume you're experiencing no issues with active memory timeouts? Have had to disable since the latest update.

✅ Smarter Active Memory ✅ Codex + LM Studio Support ✅ Critical Security Patches @openclaw 4.12 just got way better. (again)

Any other folks seeing an @openclaw error with Active Memory and constant timeouts? Worked until 2026.4.12 update. @steipete

@gailcweiner No. Active memory on @openclaw timing out. Wasted the past hour and a half debugging.

Serious question to all the AI power users out there: Are you still having fun?

@steipete @onlinedopamine Yep, strict mode was a positive step (kinda). I set rules that code changes should be carried out by a Coding agent and reviewed adversarially by the main agent. Tendency now is for main to jump in on smaller tasks, with reviewer role switched. Fewer "well go on then" moments.

@onlinedopamine Tried any of these?

what model are you guys currently using with openclaw? i switched to codex after anthropic cut of access it's been absolutely horrible so far all of my cron jobs broke, tool calling seems non existent, and it's horrendous at following instructions PLS SEND HELP

@chatgpt21 Gary Marcus blocks anyone who even remotely questions his world view. Sad, really.

Fun fact, Gary Marcus blocked me one week ago for calling him out for lying that the one of the AI 2027 forecasters had pushed back their AGI timeline when they had done the exact opposite. I had been very kind to Gary, I shared dm correspondence with him, but ever since I had called out his blatant lie he just seems like he’s been spiraling out. Saying all this about Sam on a day we’re somebody threw a Molotov cocktail at him and where his family, including his baby sleep, is quite saddening. It seems that all the care and empathy left in the world is quickly diminishing and we are just becoming desensitized and less grounded. You are allowed to criticize somebody, but I feel like time and place is very important. Kicking someone while they went through a terrifying event like this seems deeply wrong in my heart

@danveloper God I fucking LOVE Codex

God I fucking hate Codex

@coachbrucepearl Yeah, best you take your hard earned money and shove it somewhere the sun don't shine.

Looks like I'm gonna call off my summer trip to Barcelona. Think I will spend my hard earned money someplace else on vacation. Anybody with me on this?