Coding & agents𝕏
GitHub
@githubOpen the worst pull request you’ve got and try it out 👇 https://t.co/sTqDfD0F2C
Weekly perspective & original posts
AI Coding & Agents
Improve how you give agents context, break down tasks, test changes, and ship software.
Topic editions via RSS ↗Source stream
Page 10 of 32627 posts · Page 10 of 32
October 12, 2026
Coding & agents𝕏
GitHub
@githubFor the first design, we gave every dynamic block a ResizeObserver that wrote measured heights back into the layout. We built it, then rejected it. An observer that writes a height back into the layout it’s watching can retrigger itself, and the cost grows with every mounted block.
Coding & agents𝕏
GitHub
@githubAny “is the user interacting?” check has to distinguish real user input from scrolls caused by your own side effects.
Coding & agents𝕏
GitHub
@githubWhat we shipped is a recurring measurement pass, gated on idle and scoped to roughly 2400px around the viewport. Mounted blocks are ground truth. Observers normally only flag a block for the pass. They don’t write heights themselves. There’s one exception: a visible block resizing because of the user’s action can apply one synchronous correction before paint. That keeps the comment and code below it moving together without reopening the feedback loop.
Coding & agents𝕏
GitHub
@githubOne bug that held us back was “don’t correct while you’re scrolling.” It was a timestamp guard, and our own programmatic scrolls refreshed it. Toggle the sidebar, and the diff pane changes width. Wrapped lines reflow, and the surface emits a small scroll as it settles. The guard read that as your input and skipped the correction meant to keep your place. The file you were reading drifted off screen.
October 11, 2026
Coding & agents𝕏
Andrej Karpathy
@karpathyDusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less "two groups of people speaking past each other" and more a sharp funnel. - Napkin math somewhere around 6B people (~75% of the population) have barely come in contact with LLMs at all. - Around 1-2B (~20%) are casual and infrequent users of free-tier ChatGPT-like products. This group sees derpy chatbots and treats them a bit like a better Google search, a writing aid, or etc. Maybe an agent tries to book you a flight. I have non-tech friends who (reasonably, imo) say they have not much use for it at all. Even many professionals outside of math&code are in this tier. For example, execs and many other functions spend a lot of their time talking to other people, so while they understand what is happening intellectually, it is still second-hand and a bit abstract. - Now we get to professional use of frontier-grade LLMs in math&code. Somewhere around 20M people (0.2%) see first-hand that large, complex projects that used to take them weeks/months can now be completed by agents with a prompt. Building apps, copying apps, translating apps, decompiling apps from binaries... This has all happened very quickly and recently - less than 1 year ago, I was writing code manually by hand, typing memorized computer code commands into a code editor character by character, occasionally pressing Tab to autocomplete a little chunk of code. - And finally we get to the ~5,000 people (~0.00006%) with access to frontier-grade systems internally. The external world has seen the preview. It looks like swarms of thousands of agents collaborating over weeks on software mega projects: minting zero days, running cyber attacks and defenses at machine speeds, discovering new science, advancing the frontier of mathematics. Things that would have taken top professionals in the industry years of work. Meanwhile, human review and comprehension are starting to fall behind. For example, people are still involved in the "archeology" of the OpenAI-HF incident from many months ago. Mathematicians may be poring over the 722 manuscripts on frontier mathematics for a while. The funnel is driven by a combination of factors: 1. The impact scales with ambition, problem size, and horizon. A question with a paragraph answer barely stresses the system. You need a reservoir of big, difficult problems that you really care about. This aspect drives the consumer / professional dimension of the funnel. 2. The jaggedness of the system (which I have written about a lot separately). Capability peaks in domains that are digital, verifiable and economically valuable. This is because LLM capability emerges from reinforcement learning on verifiable rewards on a curated environment mixture driven by revenue potential. This aspect primarily drives the area (e.g. math&code) dimension of the funnel. 3. Access. Free-tier, paid-tier, internal. So this is the weirdness of the moment. The general public has mostly not interacted with these systems. When they have, it looks like a derpy chatbot. The majority of professionals still see only a modest uplift. And a small sliver of professionals are experiencing the vertigo of the curve going vertical. And it is all happening at the same time.
Coding & agents𝕏
Gipp 🦅
@gippp69https://t.co/gTEKJ3i4XU
Coding & agents𝕏
swyx
@swyxreupping my talk tips thread for all our lovely AIE NYC speakers. see you tmr at speaker dinner!
Coding & agents𝕏
GitHub
@githubContinuous fuzzing finds real bugs, but it still needs someone to write harnesses, watch coverage, and triage every crash. The GitHub Security Lab built the Fuzzing Taskflow to give that loop to an agent. You point it at a C or C++ repository, and it identifies entrypoints, analyzes the build, crafts harnesses, runs the AFL++ fuzzer, reads coverage, and creates a vulnerability report for each unique bug. Check out how the pipeline works end to end 🔍 https://t.co/IQhu6ZMmyh
October 10, 2026
Coding & agents𝕏
silentguy
@silentguyy66Your Grok Bot has a description field Almost everyone puts a job title in it That is why you keep repeating yourself Here is what belongs there instead ↓ https://t.co/EWxXHjYUDr
Coding & agents𝕏
hammertime
@hammertime_oneThis guy generated +$18.4M on Polymarket with a median trade size of $20.81 Horizon is interesting because it makes historical strategy testing accessible without having to build the entire research environment. https://t.co/dpfzPYKk0z Volume: $1.85B Margin: ~1% per dollar https://t.co/sX6c8Z525D
Coding & agents𝕏
swyx
@swyxaie nyc tix will sell out this weekend - last call to join us to the biggest ever technical conf in New York and our first with a finance mainstage - in some ways the final unification of both my careers: from investment bank to hedgefund, from bigtech to nyc startup. cya monday! https://t.co/KIIGQgvWcZ
Coding & agents𝕏
GitHub
@githubIn a new survey of 1,039 GitHub users conducted by GitHub and the Yale Program on Climate Change Communication, we found: • 80% were interested in tools for writing more energy-efficient code • 78% wanted to learn best practices for reducing software’s environmental footprint • 74% wanted ways to measure the environmental impact of their software or development process Developers want more efficient software. What many lack is a clear way to find waste, measure improvements, and make the case for fixing it. There’s an opportunity to turn that interest into normal engineering work. 💡 https://t.co/KiNHc9EN0y
October 9, 2026
Coding & agents𝕏
ClaudeDevs
@ClaudeDevsClaude Managed Agents dynamic workflows are now available in public beta. It's a new type of multiagent orchestration, built for your most ambitious workloads. A lead agent writes a plan that runs across many agents in phases, combining the results at the end. https://t.co/hEExShsVku
Coding & agents𝕏
OpenAI Developers
@OpenAIDevsNow in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of the most loved new features we've ever tested internally. https://t.co/0u8d2a3feS
Coding & agents𝕏
OpenAI Developers
@OpenAIDevsThe attention to detail is a little concerning.
Coding & agents𝕏
Cognition
@cognitionYou can use any personal ChatGPT plan with Devin Just connect your Go, Plus, or Pro plan to Devin and all GPT model usage will draw down from you plan's quota https://t.co/7vVFQq3IAB
Coding & agents𝕏
OpenAI Developers
@OpenAIDevsAn update for builders using Codex on Windows: We’ve built a new sandbox mode using @Microsoft’s Execution Containers (MXC) for faster setup, stronger network enforcement, and granular file access controls. Requires a compatible Windows 11 device.
Coding & agents𝕏
swyx
@swyxgoing rate for this role is between 5-50m comp package btw at the frontier agent labs
Coding & agents𝕏
OpenAI Developers
@OpenAIDevsAvailable in beta for Pro users in the Codex desktop app, for local tasks. Hit “Tab” to accept a suggestion, edit it if needed, then send. You can turn composer predictions off in Settings. https://t.co/Go9GsTLCI3