Eric

@OptimizedPort Name and shame!

I don't usually go sleuthing and I try not to go ad hominem, but this idiot appears to be far more harmful than I initially thought. The more I see, the worse it gets.

@DanielMiessler Hey! Been following you since the network chuck collab. Whats your suggestion? It sounds like humans using ai aren’t necessarily going to be immune from agi/smarter agents like mythos?

We’re missing a much bigger point on Mythos. It wasn’t even trained specifically for cybersecurity. It’s just that much better at doing work in general. It’s that good at cyber because it’s that good at everything. What do you think this is going to do to knowledge work? Mythos can chain multiple low and medium vulns together to create a high or critical. This is a task that far less than 1% of cybersecurity experts have ever done. Hell, probably less than 1% of all pentesters. So if it can do that, how do you think it’ll do at sending emails, doing analysis, writing reports, and the other 99% of everyday knowledge work? Do you really still think that Chris from Idaho has any chance competing against AI for a knowledge work job? In six months or a year, there will be very inexpensive models that can do knowledge work almost as good as Mythos. So companies have the choice of paying Chris $84,000 plus a whole bunch of benefits for 40 hours of mediocre work, or they can pay probably $100-$1000 for an AI that can do 10-1000 times the work per hour and that works 24/7. This Mythos announcement is getting attention because of cyber, but the real story is work in general.

@dvassallo CPAs hate this one trick!

Experts say

@salavat @ZixuanLi_ Same. Is the Chinese output leaking fixed too? Ty zai team!!

@ZixuanLi_ I often get answers in Chinese, which makes me thinking maybe I should learn it)

If you’ve encountered garbled output like this while using GLM-5 or GLM-5.1 on our official service, the issue is now resolved. We've patched the underlying inference-side bugs and will be releasing an article shortly to dive into the technical details and our specific fixes.

@louszbd @realsigridjin I had been using this in openclaw but noticed a lot of thinking/Chinese leaking out into the telegram messages. Is that more of an issue that needs to be fixed in openclaw harness? Ty!

we open-sourced glm-5.1 agents could do about 20 steps by the end of last year. glm-5.1 can do 1,700 rn. autonomous work time may be the most important curve after scaling laws. glm-5.1 will be the first point on that curve that the open-source community can verify with their own hands. hope y'all like it^^

@NetworkChuck @steipete Tech and the world can only offer empty promises. Still useful and exciting but we have a sure hope: Christ is risen!

@steipete Want to use it less now.

GPTEESUS HAS RISEN x.com/openclaw/statu…

@elonmusk Christ is risen!

✝️ Happy Easter! ✝️

@JamesAFurey Hell hath no furey

After 30 years of being an Atheist, tonight I will be baptized, confirmed, and reconciled to God. I cannot stop thinking about it.

@steipete “Ai spaghetti code doesn’t work”

"There’s a big wave coming" #theres-a-big-wave-coming" target="_blank" rel="nofollow noopener">mtlynch.io/claude-code-fo…

@niccruzpatane Is this the one that Elon has been hinting at?

With the Tesla Model X sunsetting, I can’t think of a better car to fill the gap. The three-row Model Y L would sell like crazy in North America.

@dvassallo Now extend this to every service. Doctors lawyers financial advisers. Everybody is cooked

CPAs think we DIY our taxes to save money. - We do it because AI will answer your 15th question about a deduction without watching the clock. - We do it because AI won't punt your return to October and act like it's normal. - We do it because AI doesn't bill you for asking "wait, why?" - We do it because AI explains what it's doing instead of just doing it. - We do it because AI doesn't have 200 other clients ahead of you in March. - We do it because AI doesn't disappear from February to April. - We do it because AI won't judge you for not knowing what a 1099-NEC is. - We do it because AI gives you the expertise without taking away the understanding. - We do it because AI lets you file at 11pm on a Sunday. - We do it because AI doesn't charge you more for having multiple income streams. - We do it because AI turns "just sign here" into "here's what you're signing and why." - We do it because AI doesn't file an extension on your behalf and call it a strategy. - We do it because AI makes you smarter about your taxes every year. Your CPA makes you more dependent every year. - We do it because AI doesn't sigh when you ask what quarterly estimated payments are for the third time. - We do it because AI doesn't care if your situation is "complicated." - We do it because you can ask AI "what if I made more this year" and get an answer in 5 seconds instead of scheduling a call. - We do it because AI won't tell you in April that you're actually filing in October.

@dSebastien Doesn’t this get noisy and bloat the vault? Does a reminder to replace lightbulb get its own note?

The problem with most task managers: your tasks and notes live in separate worlds. The fix? Turn every task into a real note. Searchable. Linkable. Connected to your projects and goals. Here's how I do it with Obsidian: dsebastien.net/tasknotes-obsi…

what if we gave you unlimited tokens for free and we also paid you

@AnxKhn @rvivek lol imagine using this as a template after it got mogged

@rvivek reminds me of : x.com/tejask/status/…

Should we hire him?

@0xSero @thdxr Let’s (opencode) go!!!

Giving away 5 Opencode Go subs Winners selected randomly from comments in 24 hours.

@onetrainops @McDonalds explain yourselves

i will vote for whichever party makes it illegal for companies to take away app reward points

@greg16676935420 What happens if you return it in the following calendar year?

If you’re working on your taxes this week don’t forget to report your income from illegal activities and stolen property

@BEBischof lmao, i'm gettign triggered

too real

@onusoz wow. maintainer is the wrong word. openclaw team are all builders!!!

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

@steipete Fix this thing i got for free!!!😡😤🤬

So much of this, every day. You really have to develop thick skin (exoskeleton?) when working on successful open source. (The Chrome extension has been removed since Google added native access in 144+, which is simpler, but yes, it does require a one-time setting change)