Sabitlenmiş Tweet
These texts I found online have introduced incredible transformation in my life. Try it out, and let me know if it works for you also:
English
Agentify.sh
3.5K posts
Agentify.sh
@AgentifySH
i love coding agents. If you use codex, claude code, gemini cli, come join us on discord https://t.co/jL7RC0v8gC
Seattle, WA Katılım Ağustos 2024
759 Takip Edilen373 Takipçiler
@schottge_menon @bdmorgan @geminicli @googlecloud also the stupid little message at the bottom like "divindg the universe by zero ... " or some cringe message while its working...who the **** comes up with these
English
@bdmorgan @geminicli @googlecloud Make it follow orders more strictly (cli), less proactively actions, obey “do not use emojis/emdash/çéäíôüà”, do not simply select two of four given orders and completely forget about the others. Talk less, act more like an engineer. Now is more about not to do instead of doing.
English
I think it's time I start speaking up a bit more on this platform. I lead engineering efforts for @geminicli and Gemini Code Assist at @googlecloud .
If I promise to post pithy thoughts and opinions a bit more, let's see if I can get a few followers...
Help me out @ntaylormullen , @JackWoth98 , @LyalinDotCom , @SriThreePO, @geminicli
English
@bdmorgan @geminicli @googlecloud Gemini CLI is not in a good spot today:
- it simply does not remember or stick with instructions
- it hallucinates and seems to just do stuff out of whim
- i can't trust it as a result of the above
- no clear pricing too many products confusing vs coex/claude
English
OpenAI bought OpenClaw
Your initial gut reaction might be anger and rage, but I promise you are mistaken.
This is a win for EVERYONE involved (including you):
• OpenClaw remains open source
• The team gets way more resources to build incredible products and advance the vision of OpenClaw
• OpenAI gains an incredible builder (Peter Steinberger)
• Get the biggest PR boost ever
• They are finally viewed as 'Open'
• Get millions of people signing up for expensive ChatGPT plans to plug into OpenClaw
• Connect their name to the most powerful AI tool ever made
• Peter Steinberger's entire bloodline never has to worry about money ever again
OpenAI will NEVER close source OpenClaw or end the project. It would be brand suicide. They have no option but to keep it open source.
Their play here is clear: incentivize using OpenAI models for OpenClaw. Get a massive reputation boost. Hire the smartest builder in AI.
This will lead to WAY more revenue for OpenAI and even more importantly: gain the favor of the millions of people who adopted OpenClaw. This will be the biggest PR win in the history of AI and make Anthropic look like closed off walled garden authoritarians for banning people the last month.
Expect faster OpenClaw acceleration, ChatGPT plans BUILT for OpenClaw, and an AI tool that will only continue to dominate the world.
This is a win for everyone except Anthropic.
Sam Altman@sama
Peter Steinberger is joining OpenAI to drive the next generation of personal agents. He is a genius with a lot of amazing ideas about the future of very smart agents interacting with each other to do very useful things for people. We expect this will quickly become core to our product offerings. OpenClaw will live in a foundation as an open source project that OpenAI will continue to support. The future is going to be extremely multi-agent and it's important to us to support open source as part of that.
English
The less you talk about building on X
The more you build outside X
English
Or join Codex. We operate with much of the same principles, incredibly small and efficient. We also select for being humble and incredible at building on top of each other’s successes.
Unique time to join, 2026 is the year where it all takes off.
Elon Musk@elonmusk
Join @xAI
English
English
😔 what are the chances the open source project survives / thrives after this?
Sam Altman@sama
Peter Steinberger is joining OpenAI to drive the next generation of personal agents. He is a genius with a lot of amazing ideas about the future of very smart agents interacting with each other to do very useful things for people. We expect this will quickly become core to our product offerings. OpenClaw will live in a foundation as an open source project that OpenAI will continue to support. The future is going to be extremely multi-agent and it's important to us to support open source as part of that.
English
fuck all your opinions about opus and codex i use gemini 3 flash as my daily driver
English
You can stay one month ahead of the curve simply by following me on twitter
Peter Steinberger 🦞@steipete
are people finally waking up
English
@JackWoth98 For one get it to actually follow and stick to instructions and not get stuck in a loop and hallucinate
I’ve given up on Gemini CLI and using codex exclusively now
English
Gemini CLI leads are all getting more active on X.
Bryan is the engineering lead and is awesome (slightly bias)
What new features do you want to see in Gemini CLI?
Let’s welcome Bryan with all our feature requests 😅
Bryan Morgan@bdmorgan
I think it's time I start speaking up a bit more on this platform. I lead engineering efforts for @geminicli and Gemini Code Assist at @googlecloud . If I promise to post pithy thoughts and opinions a bit more, let's see if I can get a few followers... Help me out @ntaylormullen , @JackWoth98 , @LyalinDotCom , @SriThreePO, @geminicli
English
@mark_k @bil0090 @GoogleDeepMind @OpenAI I’ve been using it exclusively curious how vanilla codex will turn out
English
Next week will be a VERY BIG week in AI:
* Gemini 3.1 Pro (@GoogleDeepMind)
* GPT 5.3 (@OpenAI)
* Claude Sonnet 5 (AnthropicAI)
* Grok 4.20 (xAI)
* DeepSeek V4
* ... and: Mystery model (surprise? 👀)
🚢
English
Grok … when you gonna release a serious competitor to codex or Claude or Gemini
Elon Musk@elonmusk
@raul_1329 @BasedTorba Grok 4.20 is finally out next week. Will be a significant improvement over 4.1.
English
- prone to pigeon holeing into repetitive behavior not essential to my original ask despite very explicit and careful prompts (it outright ignores or forgets)
- with UI at times it can get very stubborn and not react or listen to any new info or instructions
English
(1/3) Here's my review of GPT-5.3-Codex after 4 days of use
The Good:
- fast, its thorough, it works well
- great for UI as the quick speed gives you a fast feedback loop
- writes way better code than previous models
English
I guess now is a good time to get that Anthropic AI consultant certification
unusual_whales@unusual_whales
JUST IN: Anthropic engineers have spent six months at Goldman building autonomous systems for time-intensive, high-volume back-office work
English
Early impressions on Codex 5.3 and Opus 4.6
I spent the day vibe-coding and testing the models
Short version:
- Both models are significantly better
- Codex 5.3 is *way* faster than 5.2, which I enjoy the most
- Codex 5.3 produced more correct code than Opus 4.6
- Opus 4.6 seems better at UI and coding style
I will probably choose Codex 5.3 for mission critical code, but I think there is a lot of value in exploring Opus 4.6. Today was a great day.
Longer version:
1. On my hardest λ-calculus / debugging prompts, including real compiler bugs that, months ago, no model solved: both models nailed them. This is saturated. I need harder prompts. Will do...
2. On my HTML5 game prompt: both models produced the best output to date, but, for the first time, one scored 10/10 (no bugs, no missing features): Codex 5.3. Opus was close though, and its UI was *way* prettier.
3. On my live vibe coding: I asked both models to implement a large feature on VibiMon. Both took about the same time. Opus had 4 bugs. Codex had 2 bugs. I described the bugs, and asked for a fix. Opus still had 2 bugs. Codex had 0.
4. On implementing a toy λ-calculus evaluator and dependent type checker from scratch: both models nailed the task. This is saturated too. Opus's code was *way* prettier, but then I realized... it was literally copying my style. 💀 I appreciate that, but it means this doesn't apply...
Needless to say I have a lot to explore in the upcoming days
English
Crypto History Lesson:
When CZ worked for OKCoin he called wash trading a creative conspiracy theory.
When he quit working for OKCoin, he admitted that the wash trading bots on OKCoin were real, after calling them a conspiracy theory.
CZ deleted these posts since.
chase@therealchaseeb
super weird that BNB just magically holds up against nearly every crypto asset, yet no one uses it, knows what it does and not a single person talks about it or trades it.
English
if what this bird is saying is true then we won't hear back from that other AI expert a while back who ragequit X because he identified as a clown and tried to sue people over it for laughing.
toucan@distributionat
Twitter is reliably 3-6 months behind what’s actually going on in SF and the rest of the world is 3-6 months behind that. So in May or so there will be a big stock market adjustment to an AGI headline.
English