@alexeheath I’m seeing Opus 4.6 perform very well on Rust recently. It’s now consistently giving feedback that GPT 5.4 agrees with.
English
Akbar Ahmed
2.3K posts
Akbar Ahmed
@Akbar501
Building with AI
Palo Alto, CA Katılım Haziran 2012
466 Takip Edilen190 Takipçiler
Just me or has Opus been majorly nerfed in last couple days? On a Max plan
English
@giffmana I would have loved this the 90s when I wasted countless hours fighting with tulip drivers.
English
Coding agents are such game-changers for linux.
For almost anything that doesn't work, in the past I would have spent the afternoon, or even whole weekend, scourging forums, trying many many things, before fixing it or giving up. Now I just point codex and claude it at (and, crossing fingers, soon our model :).
Latest example: Today, I wanted to install ibkr's desktop app, a java-based monstrosity. I'm using wayland/sway on hidpi, and these two things don't go together well: fonts are awfully pixelated, and ui scale completely wrong.
ChatGPT gave up after I told it two ideas it suggested didn't work (some scaling-related env vars). Muse Spark had a nice new idea of patching its java Qt libraries, but it had outdated paths left and right. I then copy-pasted Muse Spark's idea into codex, telling codex to give it a shot and adjust as needed. And codex went ahead and did it, fetching the files out of the older versions of arch packages via curl, to patch the ibkr's built-in ones.
And it works! Now I'm enjoying the high-resolution version of the program without having to wait for months and months until the developer fixes this rare corner-case!
English
Highly refined UX that delivers better customer value will still have a place in the market. What we’re seeing is the labs becoming the “default” or “good enough” option for many, but not the best in class.
altra@catboosted
In case you weren’t aware The lab-wrapper arbitrage is coming to an end If you found economic value through the API, the labs saw it in their telemetry They’re ready to take it for themselves
English
@MatthewBerman The models are going to eat more of the harness. We build for today’s model and expect to delete a lot as models improve.
English
Betting against models getting better is foolish.
So as we build out harnesses, memory systems, etc, how are the core models not just going to eat more of the scaffolding around them?
English
@planert41 I went through this. Best thing I did was to radically improve how I eat. Hired trainer. Starting doing intense workouts. Best thing ever. You’ll get your energy back.
Also, enjoy it. It’s going to end. And when it does you’ll wish you could go back to one of those weekends.
English
Dads with young kids
Is it normal to just feel tired and burnt out all the time?
It’s like you don’t even really get the weekend to recover because it’s all just kid stuff the moment you wake up
Arguably the only personal time you have is when they nap (and you’re already dead tired by that time) or the hour after they go to bed but before you pass out
Just trying to figure out if I’m doing something wrong
English
@forgebitz Yup. It’s not a good coding agent. But I heard it’s extremely good at office work.
English
@zuess05 It can’t. As of April 2026, no AI Coding Agents are able to one shot logically complex, scalable enterprise systems.
AI Coding Agents are amazingly powerful. But building production software still requires hard work from software engineers.
English
Opus is on fire tonight. It's working through complex problems with higher quality than the recent past.
English
@HusKerrs Go on lots of date nights when he’s first born. Time your night out around his sleep time.
There’s a short window where you can still go out peacefully as a couple before he starts grabbing things. Once that starts you’ll be stuck in family restaurants for years.
English
Without a PRD … but with a lot of guardrails.
Adi Polak@AdiPolak
60–80% of Anthropic projects start without a PRD. Just Slack, context, fast pushback. No heavy docs. Makes me wonder if “good process” is just slow feedback in disguise.
English
Akbar Ahmed retweetledi
@zeeg Drums.
A gift you’d only give the children of your mortal enemies.
English
Whats the most annoying gift you can get someones five year old kid?
English
These “<big co> killed all competition with the release of <feature>” completely fail to understand the scale of these markets and, while sensational in their claims, also fail to understand the nuance and segmentation in customer needs.
Aakash Gupta@aakashgupta
Anthropic just mass-obsoleted every agent orchestration startup in a single launch. The screenshot tells the full story. That's a production fleet dashboard. 8 agents running. 247 completed tasks. Active status. MCP-connected to HubSpot, pulling deals, generating proposals, reading attachments. This isn't a demo. It's a managed production environment where you define the agent and Anthropic runs the infrastructure. The timing here is surgical. Four days ago, Anthropic blocked OpenClaw and every third-party harness from using subscription credentials. The message was clear: stop building on top of our consumer auth layer. Now here's the replacement. A first-party managed agent platform with fleet monitoring, production-grade MCP integrations, and prototype-to-launch timelines measured in days. Manus spent six months on five harness rewrites. LangChain spent a year on four architectures. Anthropic just shipped the managed version that eliminates the need to build one at all. The real bet: most companies don't want to build agent infrastructure. They want agents that work. Anthropic is pricing this into the platform the same way AWS priced server management into EC2. The 46% of enterprises citing "integration with existing systems" as their primary agent challenge just got a first-party answer from the model provider itself. Every agent startup that raised on "we make Claude reliable in production" just lost their pitch deck.
English
@PaulSolt Built our own at Sentrix.ai We optimized for building enterprise-class software.
English
Akbar Ahmed retweetledi
Three million people are now using Codex weekly - up from two million a little under a month ago. Incredible to see the growth. Thank you to all of you and to the ecosystem we’re part of. To celebrate, we’re resetting rate limits so you can keep building, and we’ll reset them every additional 1M users until we reach 10M, so we can keep celebrating along the way.
Enjoy and thank you!
English
Can’t wait for the AI generated posts on Mythos…
Mythos is not just a new model, it’s a new paradigm.
People underestimate the exponential. Mythos will change that.
English
@antirez Interesting experiment. I haven’t heard anyone mention SCSI in years.
I don’t do work at the same level of complexity as you, but I have had the same experience with using Codex for anything complex. For frontend code, TS/React I’ve found Opus to generate better code.
English
During the last week I executed very long autonomous sessions of Claude Code Opus 4.6 and Codex GPT 5.4 (both at max thinking budget), in cloned directories (refreshed every time one was behind). I burned a lot of (flat rate, my OSS free account + my PRO account) of tokens...
English
can someone besides Microsoft please make a coding harness (UI) that works with WSL?
I realize I'm a unicorn over here running Windows, but you too one day will get fed up with iOS as a desktop OS.
English