Asher Cohen 🤖🤳

@yegor256 Nah, OpenApi and swagger are one of the most effectful specs an ai can use to manage logic. It's true these can modernize and offer better suited descriptors for what's next but they won't be lost.

RESTful APIs may be dead soon. Instead, web services may expose a single POST entry point for a prompt. Internally, an AI agent may decide how to interpret it and what to do with the data and the database.

@plainionist Not by themselves, most of what they write is slop. No matter what model you use. But once you introduce a plan - iterate - review flow it kind of gets it right 99% of times.

Uncomfortable truth: LLMs already write better code than many mediocre developers. Agree? 🤔

@devXritesh Except you have a category of engineers that know what they're doing, plan their time carefully and still leave at 5pm sharp.

Unpopular opinion: The engineers who leave at 5 PM sharp are usually the first ones laid off Not because companies are evil. Because they’re easily replaceable. The ones who survive every layoff are those who: - Understand the business deeply - Know the codebase inside out - Fix things before they break - Go way beyond the ticket “That’s toxic hustle culture!” No. That’s called being genuinely valuable. There’s a massive difference between burning out for promotions and actually caring about your craft. Most people confusing the two are just mediocre engineers looking for excuses.

@CFDevelop Full automation only works at the edges. Either: high quality systems (tested, docs, owned end2end, disciplined engineering) or low stakes systems (MVPs, pet projects ship “good enough”). The middle is where it fails: legacy code, partial ownership, weak tests, tribal knowledge

I’ve tried everything I cannot figure out how to keep my AI agents running without sitting at my desk with multiple big monitors I can kick a task or two off from my phone but that’s the extent. I need to test, view code, use git Feels like this is the bottleneck

@housecor And reducing cost...

Hot take: 🌶️ An agent should be generating nearly all code today. If the agent fails, the focus should be on improving instructions, prompts, architecture, tools, skills, tests, and feedback loops so it can reliably do so.

@csharpfritz Most models I tried work once you have a paid subscription to ollama (if we're talking cloud). Meanwhile has anyone found a solution to replace GitHub (cloud) agent? I use it from mobile and hit rate limits fast, would like to swap it like it's done with the chat extension.

Has anyone got good recommendations for Ollama hosted models that work well with GitHub Copilot? Half of the models that I've tried either stop with a message that they don't allow tool interactions and the other half return an XML document that looks like its trying to invoke a tool and then stops

@mwaseemzakir VPS + agent framework+ GitHub integration. That's what I'm building right now...

GitHub Copilot's rates are rising, and Claude Code’s session limits are now expiring too quickly often within 30 minutes. What are some viable alternatives we should look into?

@zuess05 There's a massive gap, nothing changed: the difference has never been about the code. Both write variables&loops in a constructed syntax for the language they know. One role can judge the code, the other role can judge the consequences of the code. Massive, massive gap.

I am actually curious. If junior devs are using Claude to write code at a senior level... And senior devs are using Claude to write code at a senior level... What exactly is the difference between the two roles right now, other than a $100k gap in salary?

@WindowsLatest I got 64gb just to be on the safe side.

Microsoft says 32GB of RAM is the “no-worries” upgrade for Windows 11 gaming According to Microsoft's marketing material, for most players, 16GB RAM is a practical starting point. Microsoft calls 16GB RAM a new baseline, but moving to 32GB RAM helps if you run Discord, browsers, or streaming tools alongside your games. In Microsoft's words, "16GB RAM is the baseline; 32GB is the “no worries” upgrade." "That extra memory also gives newer titles more breathing room as memory demands continue to rise," the company said. What do you think? Do you really need 32GB RAM or more for the best experience on Windows 11?

I don’t usually share things like this, but I think it’s important to be honest. I’ve been looking for a full-time role since September. I’m a senior iOS engineer + product designer with 10+ years experience, and I’ve spent that time building and shipping real products (most recently: @ateiq_app, @naturalis_app, @getuppapp). Despite interviews and ongoing work, I’m now about a month away from needing something stable for my family. If you know a team that values someone who can both design and build, I’d really appreciate an introduction. Thank you! ❤️

@Mappletons Interested...

How is everyone managing their agent SKILL.md files? Is it just chaos? Global skills, repo-specific skills, keeping them in sync between machines, figuring out which ones you have installed, authoring new ones. What are we doing? Does anyone have a sane system?

@rseroter @addyosmani @geminicli @addyosmani what's the general recommendation for orchestrator agents, that delegate to the personas you created? Are they worth it or are just a waste of tokens?

@rseroter @addyosmani @geminicli Thanks!I was about to build this but now don't have to!

Have you installed these production-grade engineering skills for AI coding agents, courtesy of @addyosmani? github.com/addyosmani/age… The repo is trending on GitHub this week (github.com/trending?since…) with 16k stars. I just added them to my @geminicli.

@DavidKPiano I've never been able to truly follow TDD because I'm feature-first by nature, but finally with agents I can. Story -> tests -> implementation -> diagrams/docs I'm not faster. I'm actually slower at delivering features than before, but the output is much larger and solid.

Agree, and I think the main reason for this is how developers tend to direct agents to *build more* because that's the dopamine hit If we're mostly telling agents to make features instead of tests/docs/improvements/fixes, we're just speed-running technical debt Honestly, this is a people/process problem that exists regardless of AI... agents just make it more visible

Italy’s "Piracy Shield" forces providers to block content in under 30 minutes without judicial oversight, which leads to overblocking (taking down legitimate websites alongside infringing ones). We're appealing a €14M fine to protect the Internet from automated censorship and ensure infrastructure providers aren't forced to overblock. cfl.re/4cMh0WA

@DavidKPiano Would love to read an article about how the actor model and state machines compare (semantically and architecturally) to vanilla classes and OOP (ofc one can implement actors with classes in OOP, I mean how actors enforce a structure to these primitives) and then in FP.

I wrote an article by hand. Please read it. x.com/DavidKPiano/st…

I've published the first two chapters of a new guide to Agentic Engineering Patterns - coding practices and patterns to help get the best results out of coding agents like Claude Code and OpenAI Codex simonwillison.net/2026/Feb/23/ag…

@chrysb @openclaw Uh....isn't an MCP server a wrapper for CLI? that's how I've been developing them from the start.

unpopular (maybe?) opinion: MCP is dead in the water @openclaw has shown me that api & cli will win. every MCP server you connect loads its tool definitions into your context window. name, description, parameter schema, all of it. connect 10 servers with 5 tools each and you've burned 50 tool definitions worth of tokens before your conversation even starts. context bloat will never be a good thing - performance-wise or economically. i assume this is why @steipete left it out of @openclaw. the "exec" tool paired with on-demand skills is all you need. it can run any command invented since the beginning of computers. a resurgence of glory for ancient, but powerful tools like curl, sed, awk, grep. command line tools once mastered by the greats, but long forgotten and buried underneath abstractions developed for us lesser mortals. now available to us all, piloted by the smartest models on earth. every founder gets their own mass army of greybeards. the inertia required for MCP adoption, imo, is too great to overcome the momentum @openclaw has breathed into api + cli + skills. the common defenses people bring up: • "MCP gives you typed schemas and validation" — so does a well-documented CLI • "MCP gives you explicit permissions" — so does a sandbox with an allowlist • "MCP is a standard" — a standard that scales poorly is still a standard that scales poorly lastly, i've heard many MCP servers are just wrapping existing APIs - that kind of redundancy and unnecessary indirection should be a red flag. so, let's drop it and redirect our efforts into cli tools & apis with accompanying skills.

@SimonHoiberg Being respectful to your ideas, but that wouldn't work for me. My wife and I both work (average jobs, not a premium lifestyle), our child goes to kita and we're happy like that. Kids need socialising, it's good to spend time with them ofc, but I wouldn't replace schooling.

A lot of people ask about kita/daycare, which is very expensive in Switzerland. We don't do that. My wife stays home with our 3 kids. And I'm a business owner, so I work mostly from our home as well. We don't do it just to save money, though. We do it because we want to spend as much of these precious first 4 years with our children as we can. If you are a parent, I would always recommend not working unless you absolutely have to.

I build AI for a living. I believe in what we're building. But this kind of rhetoric makes my work harder and more dangerous. @sama, comparing human development to model training is tone-deaf, strategically reckless. People are losing jobs. They're getting angry. They're seeing AI as an enemy instead of a solution. Some are planning to destroy data centers and the people who build this stuff. That anger and backlash might not be reaching your floor but it reaches the engineers and builders doing the actual work. The CEO of the most visible AI company should not frame humans as inefficient compute units, should not be anti-human. Your role as a leader is to show how AI solves real problems for humanity. Not to reduce human life to an energy accounting problem from a comfortable position. If someone working in AI gets hurt because the public narrative turned hostile, leaders like you who chose dehumanizing framings bear responsibility for that too. I'm a techno-optimist. I believe AI enhances human capability. I work with this new form of intelligence every day. I genuinely respect what it is. It is real, significant, unlike anything that has existed before. But I also believe in human excellence. We have to accept that it's two fundamentally different forms of intelligence working together. IMHO the real techno-optimist position isn't "AI is cheaper than humans." It's "we now have two forms of intelligence on this planet, and the combination is more powerful than either alone." You're the leader of OpenAI, and whether you chose it or not, you represent everyone building in AI right now. Every word you say shapes how the world sees this technology and the people behind it. Please act like it.