I took this to heart and spent the last few hours doing another deep dive on GPT-6.2 Astra
tl;dr - things are better than when I tested, but IMO still "directionally, very bad"
I'm going to keep using the same example I've hyperfixated on since the start: "why is creating a worktree so slow?"
I had a long thread trying to diagnose perf issues while using t3 code on a particular VPS. 2 of the 3 were fast, 1 was really slow.
I asked astra outright "why is this so slow?", and it said a bunch of gibberish. I followed up with "I feel like I'm going insane, can you just tell me the cause of the slowness?"
I'll give you the answer upfront: this VPS uses a virtual disk that is slow as shit, my other VPSs have physical NVME drives that are faster.
Image 1 is from before the fixes Tibo mentioned. It shows an unnecessary graph, focuses too much on pnpm and file systems, bolds irrelevant text, and brings up ram just as much as it (subtly) mentions drive speed.
Image 2 is of Opus asked same thing. It opened with the important part in bold: "Slow disk, made worse by VDO". Ideal!
Image 3 is 6.2 Astra post-fixes Tibo mentioned. Better? Absolutely. Much more concise. Sadly, it still focuses way too much on second-order problems that are a small % of the cause. "XFS over a compression and deduplication layer on a virtual disk." - so close, but still a miss.
I think this perfectly encapsulates the problem I have with 6.2 Astra. It doesn't miss anything. It's SO thorough. But in it's thoroughness, I find it misses the most important thing: the actual point.
It wants to know everything, and then it wants to share everything. It doesn't understand what is and isn't important.
Did it say anything wrong in my screenshots? Not really. But IMO, it still entirely failed to miss the point of my question, and gave an answer that was too focused on accuracy and not enough on clarity.
In the wise words of Michael Seibel: "Most aim for 100% accuracy, and they end up with 50% clarity. Aim for 100% clarity, 80% accuracy".
Silly way of putting it, but I genuinely wish OpenAI models would lie to me a LITTLE more so I could better understand the vibe, instead of having my time wasted by all these useless details.
来聊点 AI 安全。
AI 越自由就越危险,限制越多用起来就越麻烦。最近一直在想,写代码、做运维的时候,这个度到底该怎么把握。
AI 越来越强,介入工作越来越深,安全问题也越来越多。现在连 Vercel、Notion、Cursor 这些大厂都出了比较严重的安全事件
最近也一直在做对应的调整策略,改变团队以前过于free的方式的同时不那么麻烦。等后续实践顺畅了再分享出来。
想问问大家:你们在实际工作中是怎么平衡的?给 AI 放多大权限?哪些东西坚决不让它碰?
At @teableio we used Vercel Sandbox until we saw the bill, and built our own on k8s with OpenSandbox. We expected running it ourselves to be painful, but Claude Code handled most of the Terraform and k8s work.
Same 100-sandbox math comes out to about $0.30/hr for us, roughly half of Agent37's list price. Part of that is a discount from our cloud provider. The rest is tuning for our own load: our agents need memory far more than CPU.
Given those advantages on our side, what Agent37 has pulled off is still impressive. Curious if they can turn a profit at that price.
Btw: Our users have built 10k+ team apps on this infra so far.
🎉 Introducing Teable 3.0 — The AI Spreadsheet for Business. Teams can build 100% business-fit AI workflows and custom apps, while connecting and migrating any data into one place.
✨Whether you’re a small business or an enterprise, Teable helps your team become truly AI-native.
🙌 Teable is live on Product Hunt!
If you like what we’re building, your support would mean a lot to us: producthunt.com/products/tea…
Call a Skill. Or create your own in Teable AI Chat.
📎 Built-in Skills help with files like XLSX, PDF, DOCX, and PPTX
🛠️ Skill Creator turns repeatable workflows into reusable Skills
⚡ Call any Skill later with /
See it in action 👇
Introducing Teable 2.0: The AI Database Agent
1️⃣ From the best open-source no-code DB → now the first AI Database Agent
2️⃣ Transform all your data into action: organize, analyze, automate, batch-generate — all in seconds
3️⃣ Make data work effortless & smart — for everyone
At Vercel Ship 2025, @cramforce shared a no-nonsense approach to building AI agents.
Learn how to build and secure AI agents that automate complex workflows, and understand the product and business impact behind them.