Twitter Trends June 20, 2026

The most valuable skill sets on the planet right now: 1. people who can set up agents properly, manage them, and run local AI models 2. mar...

The next hot programming language is… markdown. A minimal eve agent: 📂 𝚊𝚐𝚎𝚗𝚝/ 📄 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍 📂 𝚜𝚔𝚒𝚕𝚕𝚜/ ...

Hermes Agent has a new Blank Slate setup mode. The default Quick/Full setup modes work great for most, but if you would rather build your a...

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus ...

it’s funny that ppl calculate sending their kids to school for x years at $50k per year or whatever when the entire education system is like...

i've been building things for developers for a long time which means i have a lot of experience with api design but LLMs are making me rese...

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in ...

Most software engineers are facing an identity crisis bordering on depression. As CTOs aggressively evangelize tokenmaxxing, a class divide...

when tinder launched tinder gold (one of the most successful subscriptions of all time cuz it was pretty much ~100% margin) there was one ps...

Codex is the best agent harness out there right now If you are using it just for coding, you're doing it all wrong Literally ALL work you ...

Should founders speak to associates? The collusion in venture is wild. "I never had this attitude that you shouldn't talk to associates, mo...

One shot a general purpose agent iOS app with GPT 5.5… the general agent is powered by GLM 5.2 and it has fulll vibe coding capabilities. Pr...

GLM-5.2 isn't a great model and anyone calling it good is reading the benchmark card, not running it in a real agent loop

I'm so exhausted, these AI agents are so good I can't give out tasks fast enough for them to work on. And there are so many things I want to...

I built a tiny wardrobe for the @DataFast_ globe. You can now switch map styles: 🌚 Dark ☀️ Light 📡 Satellite 🌍 Outdoors

There is no reason to use an email drip/automation SaaS anymore. Any kind of automation can be done with a cron job and 1 prompt away. Full...

People should just use Codex as ChatGPT Since I started using Codex/Claude Code daily, I rarely open ChatGPT these days (unless it’s a quic...

When I open Codex I feel powerful. What I do on that app matters greatly. When I open ChatGPT i feel the opposite. It's supposed to be q...

codex is now my primary interface into both gmail and linear a harbinger of what is to come for established web interfaces

I get asked a lot for giant prompts to create insanely detailed landing pages. Here's how: - Copy a giant prompt like the one below 👇 - As...

For folks who make talking head videos with screen share what platform do you use? I'd love something that lets me easily zoom in and out o...

I used to be a die-hard Claude Code user. Codex has won me over because: → GPT-5.5 is excellent → Fast mode + generous limits = more reps ...

Very cool work from @jit_infinity: 🔥Leve: filesystem-first, durable agent framework built on LangGraph. You describe an agent as a direct...

GLM 5.2 + OpenCode is almost as good as Codex or Claude Code it seems. Anthropic or OpenAI cannot remove subsidies from their plans because...

The SoftBank pitch that got a billion-dollar check. "First time I met him (Masa) would've been at his house in Woodside. Considering the s...

I will go against the grain and say I can barely use up my Codex and Claude $200 subscriptions so I don’t see the point of trying local mode...

Unpopular opinion: good engineers have always vibed while coding… flow state, intuition, pattern matching. Vibe coding isn’t a new thing. I...

I’ve been thinking about how collectively inefficient agents are How many times have agents, in a silo, run into the same bug implementing ...

my monthly business goals: - MRR go up 📈 - customer support go down 📉 repeat forever

there is something about making things where the more you make things the better your taste gets and then suddenly you can make things 10x b...

GLM 5.2 nails the simulation, GPT OSS 120B tried its best. Prompt: "Write a single HTML file with a full-page canvas and no libraries. Sim...

One interesting trend: I’m seeing *so many* VC-funded, internally built infrastructure and bootstrapped solutions around “building a contex...

🚨 Next weekend is Cohort 2 of our exclusive AI workshop for Eng / Product / Design executives Zach Davis (Principal Eng @ LaunchDarkly) a...

Most people will never notice the little things in Gather. Copy a URL, and Gather instantly detects it in your clipboard and asks if you w...

One of the better agentic AI courses I've seen Nearly 10 hours of great content. Covers LangChain, LangGraph, RAG, deepagents, guardrails, ...

The highest paying job is becoming clarity. AI is getting very good at doing the work. The bottleneck is explaining exactly what you want.

Loops and checklists. This is all needed to make our agents reliable.

Any good tricks for getting the new Siri? I’m a week out and nothing.

Everyone's stacking up 7-agent swarms and there's now a paper showing a single agent with good reasoning beats most of them. I run ~95% of ...

Most people who have played a Ubisoft game could not name a single person who built the company. They know the logo, the swirl on the launch...

Your periodic reminder: https://shreyasdoshi.substack.com/p/the-problem-with-peer-reviewed-studies

The loop engineering crowd is right about one thing: the hard part stopped being the prompt a while ago. I run most real work in retry loop...

New agent benchmarks: ~89% task completion, ~2.5% unintended-harmful-action rate. Everyone's celebrating the 89. I keep staring at the 2.5....

If AI self-improvement, even in a very limited way, is possible, the cadence of shipping both AI products/harnesses & models should go up. T...

Everyone's fighting over agent benchmark scores again. Here's what months of actually running on these things taught me: the benchmark meas...

Rob Seaman, General Manager at @SlackHQ, says the rise of AI agents has helped push Slack past 1 billion messages per day: "We actually pas...

✅ Startup Acquisition #104 on @trust_mrr ✅ AI startup sold for $2,000. It creates AI influencers. Not sure why my 3% finder fee is $0 here...

This is the best resource for understanding design systems and implementing your own >Completely OSS >Design foundations (great for creatin...