Marcos Hernanz

WhatsApp search is broken, so I fixed it. Introducing ChatVault 🔒 A local-first semantic search engine running 100% in the browser. ⚡️ Rust + Wasm for vector storage 🧠 Quantized BERT model (Candle) running locally 🚫 Zero data egress (Offline capable) Open source & built with @nextjs 16. Try it: chat-vault-mh.vercel.app Repo: github.com/marcoshernanz/…

Puentes starts this Sunday. We're flying 15 of the best young engineers from Latin America to SF. They’re among the most talented in their countries, and they want to be here to compete with the best. Our goal at @antigravitysf is to help them stay. Meet the engineers 👇

@rauchg @aisdk @lgrammel Can't believe the AI Gateway is ~2M weekly downloads behind. I bet this is from people who don't know about it yet.

We've hit 10,000,000 weekly @aisdk downloads 🤯 𝚗𝚙𝚖 𝚒 𝚊𝚒 is all you need. One package, any model.

@ChrisLaubAI The biggest problem is the knowledge cutoff

Gemini is now completely unusable I was a massive fan for a long time But it's gone so far downhill it's not even funny It hallucinates results while ignoring instructions, then when you call it out and attempt to correct it, will literally hallucinate more results and then deliver them as if it self corrected. Huge disappointment

@tomfgoodwin Because LLMs are also trained on books. Em dashes are pretty common in books

Does anyone have a good explanation to why the em dash (—) is rendered out so much by LLMs The explanation is always that it's in the training data a lot. I don't think that's true at all. And why is it so hard to get LLM's to stop using them?

@nicdunz Infinite funding / consulting I guess. I've been extensively using it for the past 6 months to get all models for free

how does arena even make money

@ZackKorman This is a good move they're doing

“Improved UI for banned users” will be the title of the book on how Google lost the AI era.

@antigravity W

To the builders: we heard you. We're welcoming back everyone who recently had their Google Antigravity accounts restricted for use of third-party tools. Moving forward, we’ll have clear steps for users to restore their account if it’s restricted. To maintain the integrity of Antigravity and ensure a great user experience for everyone, using third-party tools with your Antigravity login remains against our terms. We love seeing innovation and boundary-pushing in this community, and the Antigravity team is hyper-focused on building what you need to accelerate product development. Can’t wait to see what you build!

@jack @blocks Engineers are not getting replaced by AI. Bad engineers are getting replaced by 100x engineers.

we're making @blocks smaller today. here's my note to the company. #### today we're making one of the hardest decisions in the history of our company: we're reducing our organization by nearly half, from over 10,000 people to just under 6,000. that means over 4,000 of you are being asked to leave or entering into consultation. i'll be straight about what's happening, why, and what it means for everyone. first off, if you're one of the people affected, you'll receive your salary for 20 weeks + 1 week per year of tenure, equity vested through the end of may, 6 months of health care, your corporate devices, and $5,000 to put toward whatever you need to help you in this transition (if you’re outside the U.S. you’ll receive similar support but exact details are going to vary based on local requirements). i want you to know that before anything else. everyone will be notified today, whether you're being asked to leave, entering consultation, or asked to stay. we're not making this decision because we're in trouble. our business is strong. gross profit continues to grow, we continue to serve more and more customers, and profitability is improving. but something has changed. we're already seeing that the intelligence tools we’re creating and using, paired with smaller and flatter teams, are enabling a new way of working which fundamentally changes what it means to build and run a company. and that's accelerating rapidly. i had two options: cut gradually over months or years as this shift plays out, or be honest about where we are and act on it now. i chose the latter. repeated rounds of cuts are destructive to morale, to focus, and to the trust that customers and shareholders place in our ability to lead. i'd rather take a hard, clear action now and build from a position we believe in than manage a slow reduction of people toward the same outcome. a smaller company also gives us the space to grow our business the right way, on our own terms, instead of constantly reacting to market pressures. a decision at this scale carries risk. but so does standing still. we've done a full review to determine the roles and people we require to reliably grow the business from here, and we've pressure-tested those decisions from multiple angles. i accept that we may have gotten some of them wrong, and we've built in flexibility to account for that, and do the right thing for our customers. we're not going to just disappear people from slack and email and pretend they were never here. communication channels will stay open through thursday evening (pacific) so everyone can say goodbye properly, and share whatever you wish. i'll also be hosting a live video session to thank everyone at 3:35pm pacific. i know doing it this way might feel awkward. i'd rather it feel awkward and human than efficient and cold. to those of you leaving…i’m grateful for you, and i’m sorry to put you through this. you built what this company is today. that's a fact that i'll honor forever. this decision is not a reflection of what you contributed. you will be a great contributor to any organization going forward. to those staying…i made this decision, and i'll own it. what i'm asking of you is to build with me. we're going to build this company with intelligence at the core of everything we do. how we work, how we create, how we serve our customers. our customers will feel this shift too, and we're going to help them navigate it: towards a future where they can build their own features directly, composed of our capabilities and served through our interfaces. that's what i'm focused on now. expect a note from me tomorrow. jack

Why don't we have a `.agentignore`?

@rauchg For learning, focus is still king

Engineering before AI: ◉ Ability to focus > ability to parallelize Engineering post AI: III Ability to parallelize > ability to focus

@theo GPT-5.3

Complete list of models currently worth using for code: Opus 4.6 Codex 5.3 GLM-5

@rauchg Natural language is the final form of communication

Terminals used to accept shell commands, now it’s natural language. IDEs used to accept code, now it’s natural language. Search engines used to accept keywords, now it’s natural language. Your sites & apps accept clicks, drags, hovers, taps… soon it’ll all be natural language

AGI is not even close. People forget the 'G' stands for General. No AI today is actually general. Go play a full game of chess against Claude Opus (or any SOTA model) without plugins. Watch it hallucinate an illegal move by turn 15. We have a long way to go.

AI killed the manual. Users are pasting errors into LLMs, not reading your docs. If your DevTool relies on users reading instructions to avoid breaking things, you’ve already lost. The new definition of DX: Making it technically impossible to do the wrong thing.

GPT-5.2 > GPT-5.2-Codex "We need a specialized model for our coding agent." The specialized model: Loses to the base model by 6 points. Maybe the alignment tax is real. Just give me the raw compute.

The LLM wars are saturating. The next frontier is Embodied AI (robots). But you can’t iterate hardware at the speed of software, unless you simulate it. The most valuable skill in 2027 won’t be prompt engineering, it will be building physically accurate 3D sandboxes. If you want to be irreplaceable stop building wrappers and start building worlds.

@jamwt @convex Out of the box auth (or enabling it with 1 command) The only place where supabase/firebase are ahead is auth.

What crazy new thing should @convex build this year? I don't mean like OLAP or selectable data residency or improved auth because those are already happening. Different idea? Reply with what I missed.

@Figure_robot Houses are already full of robots (dishwasher, washing machine, microwave...). The only piece missing is a robot to orchestrate them.

Introducing Helix 02 It's our most powerful model to date - it's using the whole body to do dishes end-to-end and it's fully autonomous

@bayeslord Opus 4.5 is better for fast iteration GPT 5.2 (xhigh) is better for good iteration

gpt5.2 is better than opus for coding you all have claude psychosis

We are entering the Agentic Era. Your human-facing UI is just a fallback. Your machine-facing API is the product. Optimize for inference, not clicks. UI is dead. TI is king. 👑