Carlos Herrera

@jasonlk Good to see it’s not an echo chamber

Disagree: everyone at scale should potentially look at doing a TBPN-type deal. Or two. x.com/jasonlk/status…

@oliverhenry Bro never worked with enterprise customers

Who uses word???? Serious question. Since Google docs came out that is all I used, who is paying to write word documents?

@JoeTweets915 @sameenkarim @github Their infra is handling all the slop and it’s showing

@sameenkarim @github That would be awesome to use if GitHub wasn’t offline half the time

Excited to share our progress on @GitHub Stacked PRs 🥞

@bygregorr @sameenkarim @github That’s almost impossible with a team and AI helping them

@sameenkarim @github What made you pick stacked PRs over just keeping branches small and merging fast?

@sameenkarim @github Thank u :)

Opus is nerfed today, can't edit a single line with decent code

@Yuchenj_UW Politics

How did Anthropic do automation to Word, PowerPoint and Excel before Microsoft 365 Copilot?

@bcherny can we please have ruby 3.4 on claude code's sandbox? 3.3 is the latest and this is 3 years old, thanks

Claude code skills are the virus of Mac. It's like downloading an .exe in the 90s just in markdown format

@alz_zyd_ @Jbuehler2000 He really disliked to work on LLM models

@Jbuehler2000 x.com/i/status/20422…

Lol firing Yann, hiring Wang, and setting a couple billion dollars on fire poaching talent seems to have actually worked for building a decent model

@sundeep That’s jcal

Incredible time to be in tech!

@dabit3 @DevinAI What about getting cancelled?

At Cognition we're seeing coding agents handling the entire SDLC, going way beyond just coding. Here are some tips and tricks we're seeing dev teams use with agents like @devinai to handle the SDLC: 1. Scheduling daily E2E smoke tests: an automation signs up for your app, goes through onboarding, exercises core flows, and gets a pass/fail report in Slack every morning. You can even watch the screen recording or have it sent directly to you via Slack. x.com/ryancarson/sta… 2. Auto-triaging production errors: it's easy to wire Sentry (or other) webhooks so new errors get root-caused, fixed, and shipped with a regression test before an on-call even has to look at their phone. docs.devin.ai/api-reference/… 3. Scheduling weekly dependency updates: a scheduled session checks for outdated packages, runs your full test suite, and opens upgrade PRs grouped by patch, minor, and major bumps. Merge what's green, review what's not. docs.devin.ai/product-guides… 4. Morning health digests: a scheduled session queries Datadog for error spikes, latency regressions, and failing monitors, then posts a severity-rated summary to Slack before standup. 5. Auto-fix on every PR: Sophisticated review agents like Devin Review catch bugs, security issues, and style violations on open PRs, then automatically push fixes directly to the branch. No back-and-forth in review comments, the agent handles the entire loop. cognition.ai/blog/closing-t… 6. Parallelization of large migrations: for instance scope a REST-to-GraphQL or JS-to-TS migration, split it into conflict-free work packages, and run 8+ sessions in parallel. 7. Scheduling feature flag cleanups after releases: teams leave flags in place as a kill switch after new launches, then never get around to removing them. You can set a one-time session for a week after ship day and the cleanup actually happens: dead code path removed, tests updated, PR opened. (done via Scheduled Sessions) 8. Weekly changelogs: once per week, a scheduled session groups merged PRs by category (features, fixes, improvements), posts the digest to Slack + anywhere else relevant, and updates CHANGELOG.md 9. Reproducing customer-reported bugs from support tickets: paste a customer issue into Slack, tag Devin, and it attempts to reproduce the problem in the browser. You get a screen recording of the reproduction and a filed bug with exact steps-to-reproduce attached. 10. Enforcing your design system: schedule a session that scans merged PRs for hardcoded colors, missing design tokens, style violations, etc... Auto-creates tickets or kicks off sessions for anything that slipped through. 11. Auto-generating API docs from a ticket: create a docs Playbook, sync it as a Linear label, and apply it to any ticket. Devin generates documentation following your conventions and opens a PR. 12. Keeping docs in sync with code changes: schedule a daily session that reviews the previous 24 hours of merged PRs against your documentation. If an API endpoint changed, a config option was renamed, or a feature works differently now, it opens a PR to update the docs before users hit stale information. 13. Racing competing solutions against the same problem: if have a slow API endpoint you launch 3 parallel sessions, each trying a different optimization strategies (caching, query rewrite, denormalization). Compare the benchmarks and merge the winner (this can also be automated) 14. Automated visual regressions tests before every PR: add a repo skill that triggers whenever UI files change. Devin starts the app, screenshots every affected page at multiple viewports, and flags layout breakage, overflow, or missing elements (or you can have Devin autofix them) This type of work is already partially being automated by a lot of teams, but usually by a human in the loop meaning they're taking time away from more important work to do things that don't usually provide immediate impact or business value It's obvious that automating these repetitive tasks frees up engineering time, but to me it's also not a bad recruiting tactic - if you work here you won't be spending any of your time doing boring work.

@typesfast It’s using the same filter ladies use on IG

Wait, the moon isn’t all grey?

@bridgemindai But local models are shit for coding

Claude Code rate limited me so hard I bought a $5,000 NVIDIA DGX Spark. Arriving tomorrow. A personal AI supercomputer. Anthropic cut off OpenClaw users. Slashed Claude Opus 4.6 rate limits. Told $200/month Max plan customers to use less. Then gave us a credit as an apology. This is what happens when AI companies have too much power over your workflow. One update and your entire stack breaks. Local models are the only infrastructure no one can throttle. No rate limits. No 529 errors. No surprise policy changes. Tomorrow I'm testing the DGX Spark live on stream. Running local models through real vibe coding workflows. The goal is simple. Never depend on a single provider again.

@0xCodyS @tri_dao It can be fast if it’s shit

>Sees insane GLM-5/Kimi-K2.5 speeds >Looks inside >@tri_dao every time.

@RealDanODowd Dude sure

In case you were wondering why Tesla self-driving is so dangerous, this guy is a senior member of the team developing it. He claims he has no idea how to handle approaching a road that's completely obfuscated by smoke. Hint: the answer is to slow down and proceed with caution, which this Tesla didn't.

@HolySmokas Go to Italy

What should I do?

@mark_k @xai Ok let me wait until I build anything useful to help @elonmusk . Biggest fumble in AI

@mark_k @xai But without tooling means nothing

Grok 4.20 is criminally underrated. Don't let the haters distract you, try it for yourself. @xai was seriously cooking with this model. And it's just the beginning, a stronger version is coming soon.

@mil000 Without checking probably Forbes 30 or YC

this means no one is using their software. If you are actually successful you never start a free tier

@elonmusk when grok cli for coding outside cursor et al