People were dissing about Terra that it should be removed. But I think Terra & Anthropic's Haiku will have a user base. Low end models need to find the right adaptive use cases. But yeah, it shouldn't be for these flashy video-graphic demoes. Hope this has a reasonable consumption of credits.

Just crossed 1800+ followers ! 200 away from 2k. We keep the community strong and circle of builders growing ! 🙌 Let’s connect if you are a builder in this space ! 🎃

If you're building an AI agent with memory, don't immediately reach for a vector database. First, figure out what you need it to remember. These 5 patterns solve different problems: 1. Use structured profiles for confirmed facts like a user's preferred language or a project's runtime. Save them in database fields the agent can look up by ID. 2. Use conversation summaries to carry decisions and unanswered questions into the next session. Keep the original messages available because summaries can leave things out. 3. Keep a task journal of what the agent tried, what failed and what worked. Before another attempt, it can check that history instead of repeating a failed approach. 4. Use retrieval memory when you have too many documents to load into every prompt. Search for relevant passages and include their sources so the agent can check them. 5. Use persistent files for scripts, notes and unfinished work. The next session can open the actual files and continue where the previous one stopped. Pick one thing your agent keeps forgetting and fix that first. If your agent forgets your project settings, save them somewhere it can read next time. If it needs to reuse a script, keep the file between sessions. You don’t need a vector database for either.

Post your heart out ! Your biggest fear is that someone will see how much you care and find it fucking ridiculous. So you reread what you wrote, remove the sentence that feels too personal. Add a joke so nobody thinks you’re taking yourself too seriously. Eventually, it’s safe enough to post. You’ve removed everything you wanted to say. The same thing happens with niches. At first, the niche helps people find you. Then, slowly, it becomes a character you have to keep playing. You post about the same topic, in the same tone, from the same angle. Not only because the algorithm rewards consistency, but because people have started to expect a certain version of you. And once people know you that way, breaking character can feel like letting them down. You wonder what will happen if you talk about something outside your niche. Will people unfollow? Will the post perform badly? Will they decide you’re no longer credible? Will the algorithm stop knowing where to place you? But underneath those questions is often something more personal… What if people see that I’m more than the image I built? So you edit yourself back into the role. You remove the story that doesn’t fit, turn the opinion into a lesson, make the post useful enough to justify its existence. Eventually, it’s safe enough to publish. You’ve removed everything that made it yours. I think this is why people stay trapped in their niche long after it stops feeling alive. The niche is no longer just a content strategy but a protective shell. If you stay predictable or keep speaking from the same position, nobody can question who you are. Then people praise you for being consistent. But consistency can quietly become self-abandonment. You’re allowed to talk about something that doesn’t fit neatly into your content pillars. You’re allowed to have interests your audience didn’t subscribe for. You’re allowed to change your mind, try a new voice, or post from a part of your life that doesn’t support the character you’ve been playing. You can keep parts of your life private. You can also let one honest sentence through without explaining why it belongs in your niche. Your audience may have found you for one thing. That doesn’t mean you have to remain only that thing. Let people meet you while you’re still changing.

Cloudflare's AI code reviewer flagged nearly 230,000 engineering violations. Almost 16,000 of those caused merge approvals to be withheld. Here's how they built it, and what you can steal for your own coding agents: 1. Maintain a shared, versioned engineering rulebook writing down your security, architecture, APIs, error handling, etc. 2. Separate recommendations (SHOULD) from mandatory rules (MUST). 3. Review rules before enforcing them. Cloudflare approves new rules first, then moves them into enforcement after teams have time to adopt them. 4. Load only relevant rules. Review architecture documents before anyone writes the implementation. 5. Use linters for mechanical checks. They're fast and predictable. Let AI handle the reviews that need context and judgment. 6. Review incident reports for missing timelines, detection signals and follow-up actions. Now here's something you can try with Claude Code or Codex today: - Ask your agent to inspect your repo, lint config, CI checks and architecture docs. - Have it propose 10 repo-specific MUST/SHOULD rules, with reasons. - Review and approve those rules yourself. Save them in AGENTS.md or CLAUDE.md. - Then have your agent review each PR against them, citing the exact file, line and violated rule. It's a pretty useful way to stop your coding agent from repeating the same mistakes across PRs.

In 2003, Dario Amodei the current CEO of Anthropic shared his Anti-war stance as a sophomore at Caltech. Do you think the company still stands by that spirit ?

I tried something different this week. Posted less, and focused on sharing things I genuinely find interesting and useful. One of those posts crossed 11K impressions. It's a small experiment, but it feels good knowing I can nerd out about things I love, help a few people along the way, and still reach an audience. Thank you to everyone who reads and supports my work. 🌻

Dessa voice model is SCARY good, almost unsettling. I just listened to the samples, and it laughs mid conversations, gasps under its breath, throws in little “yeahs” and knows when to interrupt, ridiculously human style. We've had real time voice models like OpenAI's and Moshi for a while. They can process speech directly, but still rely on pretrained language models or text during training. But Block took a pretty wild approach with Dessa. They trained it from scratch using ONLY human conversations. That is extremely difficult. The model had to learn language AND all the messy things we do while speaking, around mannerism like sarcasm, hesitation, emphasis, timing, interruptions, even when to laugh. :3 All of that from sound alone. And apparently, the whole thing was trained on a single NVIDIA GB200 NVL72 and can run locally on an M4 Max MacBook. If these demos hold up in real conversations, we're getting dangerously close to a world where you can't tell who's on the other end of a call.

I am telling you the competition next year will be insane ! Kimi 3.1 Pro is only ~3 points behind Claude Opus 5.5 in several intelligence indexes. It overtook leading SOTA frontiers like OpenAI GPT-6 Astra & Google's Gemini 4 Argon. Best thing, they are launching their open weights on Nov 4th !

99% of financial advice on the internet is ABSOLUTE garbage. And some of the worst advice gets repeated in your motivational pep talks so often that people actually believe it. Here are 10 terrible money lessons you should probably unlearn: 1. "Your 9-5 won't make you rich." A high income, disciplined spending, and years of investing can build serious wealth. (No, not a billionaire) 2. "Renting is throwing money away." So are mortgage interest, repairs, property taxes, and buying a house you can't afford. 3. "Follow your passion." Being passionate about something doesn't mean anyone will pay you for it. Get really good at solving valuable problems. 4. "Save 10% and you're set." 10% of what? Your income, lifestyle, and retirement goals matter a hell of a lot more. 5. "You need to hustle 24/7." Sleep deprivation and burnout aren't wealth-building strategies. 6. "Never use credit cards." Use them responsibly, pay the full balance, and take advantage of the benefits. Don't pay interest to chase rewards. 7. "All debt is bad." Borrowing to buy a depreciating toy and borrowing to grow a profitable business are two very different decisions. 8. "Buy the house the bank approves." The bank decides how much it'll lend you. You decide how much financial stress you can live with. 9. "Crypto is the future." Maybe. But anyone promising guaranteed returns from something they can't predict is selling you bullshit. And I've been in the trenches . 10. "Stop watching Netflix and you'll be rich." If your income sucks, cancelling a $15 subscription won't magically fix it. Focus on the big numbers first.

Anthropic's latest research on formal verification is pretty fascinating, and I will try to explain that in simple words. Normally, when developers test software, they throw millions of different inputs at it to see if something breaks in the system. But even after a million successful tests, there's always a chance the next input could crash the program. That's where formal verification comes in. The idea is pretty simple. What if you could use mathematics to prove that your code won't crash, for every possible input within certain limits? We've been able to do this for decades, but writing those mathematical proofs takes an insane amount of time and expertise. So Anthropic got Claude to do the heavy lifting. Claude looked at the actual compiled code and worked out the mathematical proofs, then it passed them to another tool called Rocq to check whether they were correct. And while doing all this, it discovered bugs that had gone unnoticed despite years of testing. The researchers ended up generating 180 MILLION lines of proofs across 123 open-source libraries, covering 239 test entry points. What's really interesting to me is that we don't have to blindly trust whatever Claude generates here. The mathematical proof gets checked independently. Of course, proving that certain parts of a program can't crash under specific conditions doesn't mean the entire program is bug-free. But imagine being able to run mathematical proofs on your code as easily as you run unit tests today. I think that could change software engineering quite a bit.