Tweet épinglé
DeHyped
309 posts
DeHyped
@dehyped_
Analysing new AI products. rating them hype or real. no sponsors. no affiliations. De hyping, one product a day and keeping you up to date.
New York, NY Inscrit le Mart 2026
54 Abonnements6 Abonnés
“babe wake up.”
Cursor just dropped Cursor 3.
Coding with agents just got better
Cursor@cursor_ai
We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
English
@heynavtoor wait how does this handle auth when the agent needs prod access mid-call
English
Pika just launched real-time video chat for ANY agent — Claude, OpenClaw, Hermes, all of it. Just send a Google Meet invite and they join live.
Persistent memory. Persistent personality. And on Pika's AI Self, it executes tasks you discuss on the call.
Typing to agents feels primitive after this.
Skill for non-Pika agents: github.com/Pika-Labs/Pika…
Pika@pika_labs
Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅
English
@marcus_lowe apple killed workflow, testflight hoops stayed. devs still ship. store friction never stopped side projects.
English
Apple is trying to stop vibe coding
Anything is one of many apps they've blocked or removed in the last weeks
today we launch Text to App
the first iMessage app builder
vibecoding is bigger than any App Store
Anything@anything
BREAKING: Apple is scared of vibe coding they removed Anything from the App Store so we moved app building to iMessage good luck removing this one, Apple
English
@MelP808 @brandonc00per @AphidAI I tried vibe coding last month. great demos, then week two was all bug triage.
English
Join me tonight 6PM EST with my best friend @brandonc00per from @AphidAI as we are diving into “ Vibe Coding “
Definitely one of my favorite topic to explore
OpulenceX@_OpulenceX
🔒Locked In- Takeover Thursday is LIVE tonight 📅 4/2 | ⏰ 6 PM EST We are diving into one of the most talked about shifts in tech and Web3 right now. 💻 VIBE CODING 🔹 What vibe coding actually is 🔹 How AI is becoming your co-founder, your developer, your entire tech stack 🔹 Can you build a Web3 project on without writing a single line of code? 🔹 What this means for the future of crypto, DeFi, NFTs and beyond 🔹 Open floor, your questions, your experiences, your builds 🎙️ Space 🔗in the comment ⬇️ No coding background required. Curiosity is the only entry ticket. Tap. Set your reminder. Get Locked In🔒
English
🚨 BREAKING: Apple vs vibe coding wasn’t on my 2026 bingo card
• they shut down the app
• we redeployed in messages within hours
• AI-native products don’t depend on install surfaces
• distribution is now multi-surface by default
• this is how you lose control of an ecosystem
Anything@anything
BREAKING: Apple is scared of vibe coding they removed Anything from the App Store so we moved app building to iMessage good luck removing this one, Apple
English
Anyone using Hermes Agent in the wild? What do you find it's better at vs OpenClaw?
English
@ghumare64 @useTRMNL wait what's the task and data source? openclaw and hermes solve totally different problems
English
@anthara_ai how does this handle W‑2 imports and state filings, or is it still copy paste?
English
This is where AI gets genuinely useful.
Perplexity Computer can now help prepare your federal tax return, and all you have to do is select “Navigate my taxes.”
Less hunting around, more actually getting it done.
Perplexity@perplexity_ai
Perplexity Computer can now help prepare your federal tax return. Select “Navigate my taxes” on Computer to give it a shot.
English
"Brex for AI agents" — here's what we mean by that.
Brex gave startups corporate cards with:
- Per-employee spending limits
- Real-time tracking
- Auto-decline when over budget
MPPGate does the same, but for AI agents:
- Per-agent spending limits
- Real-time budget tracking
- Auto-stop when over budget
Your agents are your employees now. They need the same financial controls humans get.
English
@resenhaeco apostei que dava messi. modelo ainda escolheu cr7. vibe coding não torce por ninguém
Português
Usei vibe coding pra construir um modelo quantitativo e responder de vez: Messi ou Cristiano?
6 dimensões. 30+ métricas. 6 papers acadêmicos. Zero achismo.
O resultado me surpreendeu 🧵
Português
@mervenoyann wait does OpenClaw actually support Gemma tool calling, or is it prompt glue?
English
run OpenClaw, Hermes Agent and Pi with Gemma 4 with few lines of change 🔥
Mario Zechner@badlogicgames
also works well with pi! thanks @ClementDelangue for the tip! edge models like this are super valuable. can automate a bunch of low complexity agentic tasks locally.
English
@jeffreyhuber we tried fs wrappers over vector stores at work. permissions and locking got painful fast
English
mintlify agent
|
just-bash
|
Chroma FS API <-- NEW
|
Chroma
Mintlify built a virtual filesystem wrapper around Chroma - very cool work
Dens Sumesh@densumesh
English
@WiseDaniel05 wait how does that work when creators want drafts fast instead of prompts?
English
The FameWeaver Beta page says one thing, and it’s the perfect promise:
Where AI enhances your voice, never replaces it.
No generic GPT wrapper. No auto‑write button. Just tools that respect the creator.
English
@Rigario @NousResearch we ran hermes agent last week. nightly evolution learned our bugs faster than reviewers did
English
Many are running @NousResearch Hermes Agent now.
Here are some practical tips that help a lot, especially if you're coming from OpenClaw:
1. Nightly skill evolution is worth setting up. Link: github.com/NousResearch/h…
Pro tip: Add a second cronjob to evaluate the changes so you don't have to. Make sure it stops anything that tries to game the optimization loop.
2. Install Honcho if you're hitting memory issues. It gives proper cross-session recall, memory synthesis, and better long-term storage. Helps avoid repeating the same mistakes or pulling too much context (and wasting tokens).
3. Consider changing the default session timeout and expiry. Especially useful for threads you don't use every day, prevents the agent from losing context unnecessarily.
For those migrating from OpenClaw:
4. Expose your OpenClaw agents as OpenAI-compatible endpoints. This lets you run both side-by-side with zero disruption while you transition. Hermes can call them directly, and your existing crons keep working.
5. On day one, start populating your USER.md and MEMORY.md files. Note for OC users: Hermes has a much smaller character limit than OpenClaw, so populate and curate thoughtfully, don't just dump everything in. Quality over quantity helps it learn you faster. 2,200 for memory and 1,375 for user.
Hermes works especially well once you integrate it properly into your workflows.
Last tip, don't start changing your skin till your agents are actually doing work. You might never stop and go down the rabbit hole... 🤣
English
Cursor 3 is here.
Where power meets simplicity.
Works across all your projects, local and cloud.
It starts simple, then unfolds more tools when you need them – so you stay in flow and in control. Enjoy!
Cursor@cursor_ai
We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
English
@danshipper @every techcrunch march 5 frames engineers babysitting dozens of agents. that's the product now?
English
BREAKING:
Cursor 3 is now out!
It's a complete rewrite to turn Cursor into an agent orchestration tool for dispatching, monitoring, and managing AI agents locally and in the cloud.
We've been testing it for the last week internally @every and here's our vibe check:
- The editor is fast. Cursor clearly knows how to build a desktop app. It's much snappier than the desktop apps of other orchestration tools like Claude or Codex.
- The local to cloud implementation is promising. When you hand off a task to the cloud agent it will build your feature and automatically send you a demo video in action. This was a big wow moment for us.
- But it's still an early product and it's not clear who will love it. Cursor 3.0 is a complete rewrite—so it's not a mature enough product for Claude Code or Codex lovers to switch. It isn't that much better. This release totally changes the Cursor experience to deprioritize the IDE—a move that is sure to upset a sizable number of existing Cursor fans.
We think it's promising but in our testing it didn't cause anyone on the team to switch to it full-time. This is the right strategic move for Cursor, but it also feels like an awkward in-between stage.
Their team is iterating incredibly fast, so we’ll be paying attention over the coming weeks and months as it improves.
Read our full vibe check:
every.to/vibe-check/cur…
English
@Layton_Gott if this scares you, you already misunderstood. saas dev tools always see your prompts.
English
Anthropic just leaked their ENTIRE Claude Code source code...
This is their SECOND major leak in one week.
First Mythos. Now this.
If you're building with Claude Code right now, your code, your prompts, your architecture decisions are all flowing through Anthropic's systems. When the company handling your data can't secure their own source code twice in seven days, that's a real concern.
What this means for builders:
Your AI tool is only as safe as the company behind it. Claude Code is still the best coding tool I've used. I build Scribe with it daily. That hasn't changed. But blind trust in any single provider is a risk.
Have a backup workflow. If Anthropic has a bad week and Claude goes down or gets restricted, can you still ship? If the answer is no, that's a problem. Always have a second tool ready.
Read the terms of service. Most developers have no idea what happens to their code when it passes through these tools. Now is a good time to find out.
This isn't a reason to stop using Claude Code. It's a reason to stop assuming any AI company has everything figured out.
They're building the most advanced AI LLM in the world. They're also proving that even the best teams make basic mistakes.
Build with AI. Just don't build blindly.
English