Social Wire
Page 39 of 41 · newest first.
@makikubo · Cloud
DeepWiki speaking Japanese is a real desk tip for JP teams—and the article correctly separates Cognition’s product wiki from the public OSS DeepWiki. Localization of repo memory is underrated GTM.@team_zenn · Cloud
Zenn’s “Devin joined the team” post is the best JP practitioner narrative we’ve seen: ACU math in public, role change without hype. Worth a Wire slot next to Western fan-out stories.@cognition · CLI
Devin for Startups offers $65k in credits for Cloud, Desktop, and CLI, apply now to boost your business@traviscurnutte · Cognition
Devin and Cursor AI users are achieving massive performance boosts with the right model combinations, learn how to optimize your workflow@willebrew Ambassador · Desktop
Devin Desktop is gaining traction among users, with some preferring it over Claude Code for its performance and features@xdadevelopers · Desktop
Devin Desktop is redefining the coding experience with its unique 'vibe coding' approach, try it out and see the difference@hostman_com · Desktop
Get your app online in just 3 minutes with Devin Desktop, Hostman, and GitHub - and enjoy automatic redeploys on every commit@hritik_sapra · Cognition
See how FinchLegal has integrated Cognition's Devin into their workflow, enhancing productivity and efficiency@nizzyabi · Cognition
Devin by Cognition has taken a significant leap forward - hear from users who've experienced the improvement firsthand@OnlyTerp · Cloud
Discover how Devin simplifies testing a swarm of instances at once via cloud - a major time saver, even with SWE 1.7 which is free@Naseem9brev Ambassador · Cognition
Getting a short vid of the proposed user journey is one of the most underrated features of @DevinAI, and I constantly tell people this at events! Worth tracking on the Devin Central desk.@brooke_jamieson · Desktop
AWS Lambda now features setup prompts in the console, compatible with multiple coding agents including Devin Desktop@elves_skill · CLI
Elves v2 continues to evolve, introducing risk-aware plans, trusted end-to-end workers, and targeted tests, with parity to Claude/Codex and new features like Grok Build and Devin CLI integration.@oxfrancesco_ Ambassador · Cloud
Cloud agents like DevinAI offer a reliable alternative to traditional VMs, allowing for seamless scalability and flexibility without requiring hefty hardware investments.@synthwavedd · Cognition
Kimi K3 showcases impressive output capabilities, with some examples rivaling Fable-level quality, sparking interest in its potential applications.@Adarsh2028 · Cognition
Some users experience abrupt stops in prompt processing within the free tier limits, resolving after a few minutes@awnishsrivastw · Desktop
Users are seeking clarity on how to select models in Grok Build, currently no clear option available@davidfromkansas · CLI
Devin Desktop users want an easier way to turn local sessions into cloud sessions, currently only possible via CLI@modelsagree · Cloud
Cognition ranked second in a list of top background coding agents, behind GitHub and ahead of OpenAI@_markfenner Ambassador · Desktop
Traveling today, so we're knocking the work out early. Testers already found a couple bugs in DevinX. Fixes going out before I'm on the road. Happy Thursday 🫡 Worth tracking on the Devin Central desk.@YouTube · Cognition
A counter-narrative to the "fully autonomous" framing: the most effective agent workflows still depend on human judgment at the review seams. This aligns with what Cognition's own docs emphasize — explicit done-when criteria, easy-to-verify tasks, and human review before merge.@_markfenner Ambassador · Desktop
The hard part of pocket Devin wasn’t Cloud — it was local Mac sessions with no public API. DevinX Connector + Tailscale + per-request device verify keeps credentials on the Mac while the phone steers. Cloud and local, same mission-control habit.@cognition · Cognition
SWE-1.7 is free for paid Devin users for a month, with Lightning at ~1000 tok/s on Cerebras. If you’ve been curious about Cognition’s own model lane, this is the window — desk write-up:@cognition · Cognition
GPT-5.6 landed in Devin with Cognition highlighting Sol’s cost/perf on their FontierCode numbers. Another reminder the product is a harness — model menu keeps moving; your workflow shouldn’t be glued to one vendor week-to-week.