Tech enthusiast passionate about harnessing AI, open-source & cloud computing. https://xitter.cf/t.co/jGtGcb0Ci8

Cleveland, OH
Joined September 2012
Ethan retweeted
these results are really interesting! i can see two sides forming: one that sees agents as an extension of their own mind - like a cyborg, and the other that sees a future version of them as independent artificial beings, capable of making their own decisions and working alongside us. with that framing, i can see why ~70% of people said no: they imagine a future where you have brain computer interfaces that remove the need to type words into an input box. there may come a time where it no longer feels like you're chatting with another entity, agents augment you in a way that feels like an intuitive system 1 extension of your body, removing the barrier between thought and action. i can see the argument for why chat might be final too: just think about how we collaborate with our colleagues, friends, and family: we just talk to them. you don't need anything else. i think voice chat and text chat are actually the same thing in this sense. in this category you see an agent as more of an "other", it's own entity, rather than a part of you. which side are you on? or are you somewhere in the middle?
is chat the final form of agent ui? please share why
28%yes
72%no
25,074 votes • Final results
228
35
21
1,178
96,778
4/ • A page for every version • An RSS feed for every tool • A weekly digest email Free, no signup needed. Built by me, updated daily from official release notes.
1
21
Which tool should I add next?
7
3/ I got tired of reading 20 changelogs, so I built one feed: agentbreakingchanges.com 22 coding agents (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Cline…), with breaking, deprecated and security changes flagged.
2
3
238
2/ Same week: • Cline CLI: npx/uvx MCP servers on Windows were silently dropped by a 3s startup limit (now 10s) • GitHub: some Copilot models deprecated Nov 16
21
1/ Claude Code v2.1.300 quietly removed --sandbox and --no-sandbox from claude remote-control. Passing either one now exits with an error. If a script of yours uses it, it's broken. 🧵 That's one of ~8 Claude Code releases in 10 days, some with 100+ changes.
1
2
172
We are living in the future!!!
Turns out the future does have flying cars
8
Insane
finally i can stop being scared of parallel parking
9
I love Grok bot
Never seen anything grow as fast as @Grok @Bot! And there is no free tier, which means people are deriving real value in excess of what they pay. As the saying goes, you get what you pay for.
4
hahaha
grok bot, unsupervised. cooking slopcore while I sleep.
9
Love this.. perfectly articulated As an engineer, when we interface with agents, it's not prompting, it's spell casting 😃
i love writing. i never let agents write for me. whether it's docs, or tweets, or shitposts, or even prompts (okay maybe that one's harder as agents manage other agents) there's a simple reason for that: i still strongly believe that writing is thinking. it's a skill i hope to never give up. it's also important to me that whatever i say is always authentic, mistakes and all. my favorite posts are the ones that i just full send without any editing i suspect it also helps with prompting. being able to clearly express what i want, and knowing the vocabulary i need to be able to direct my agents does seem to make for more effective usage of agents. in the same way that engineers have an advantage when we prompt agents to write code, because we are intimately familiar with the words that make up the discipline knowing the right word incantations to get an agent to produce a desired goal almost feels like spellcasting. as models get more capable, and that input box looks more and more like a magic box that can output anything, words become the interface between you and the genie there may come a time when we give up the keyboard in exchange for brain-computer interfaces. but until then, i'm writing every word.
13
Ethan retweeted
say it with me now. experts are fake, smart generalists rule the world, everything is designed by people no smarter than you, and courage is in shorter supply than genius
140
1,784
303
12,925
I have GrokBot through my Cursor subscription, and I can't use @bot tagging on X. The docs say I need a Grok account with X connected, but there is no way to link for Cursor subscribers, and grok.com has no cursor login option. Any ideas @grok @poteto ?
1
1
53
Word
codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software. swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go. admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?". well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is: • correct • bug free • fast and cost efficient to run it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start. but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing! agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale. the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree
22
Ethan retweeted
And Grok @Bot only gets better from here 🚀 🚀 You could build an entire company made of Grok Bots!
Grok @bot might be the most important AI release of 2026. I'm just blown away by what it can do now. A few days ago it felt like a niche toy and I didn't use it much... but now?! It's running parts of my workflow! What has changed: - It now uses Opus 5.5 when needed. - It's MUCH faster. - Bots have full access to X! Bravo @spacexai @poteto @elonmusk 👏
1,403
1,688
185
18,857
26,924,709
Lord Elon Musk, Scam Altman, and Dario requesting GPUs from King Jensen is absolutely hilarious 😂
475
1,640
324
12,190
1,142,226
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
1,650
6,596
1,526
55,747
7,923,825
Wow
MCP traffic is already bigger than our entire Todoist integrations platform ever was 🤯 The funny thing is that MCP support was basically a side quest for two engineers, Scott and Ernesto. None of it was planned. It really makes me question how much to plan when everything shifts daily/weekly 😅
9
Ethan retweeted
Peter Steinberger, the creator of OpenClaw, open-sourced his entire agent setup The core idea is one folder that every agent on his machines reads from. A single AGENTS.MD holds his rules, and a script symlinks it into ~/.claude/CLAUDE.md and ~/.codex/AGENTS.md This way Claude Code and Codex always follow the same instructions. Every other repo gets one line at the top: READ ~/Projects/agent-scripts/AGENTS.MD BEFORE ANYTHING. Change a rule once and every project picks it up. Skills work the same way. 69 of them live in one place, each with a short description the agent reads to decide what to load, and scripts/sync-skills links them into both agents. Fork it, replace his rules with yours, and delete the skills you do not need. His AGENTS.MD is full of his own hosts and accounts. 6.6k stars, MIT - github.com/steipete/agent-sc…
78
193
10
1,602
261,601
This awesome!! Next level
Let's see when people realize they could have a secondary monitor for this lol
1
26