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 34 of 36
717 posts · Page 34 of 36

September 22, 2026

Coding & agents𝕏

See what’s being reused and what’s preventing cache hits. Track cache-hit rates in the new Prompt Caching Dashboard on https://t.co/9eDbe9PbGF. Use the diagnostics API to identify changes that prevented reuse and estimate how many tokens were affected. https://t.co/M16n4rG1Cl

Media from the original post
♡ 152 likes↻ 4 reposts↳ 4 replies
Collected original
ThreadExternal link
View original post on X ↗
Coding & agents𝕏

🚀 Claude Opus 5.5 is now available in VS Code with GitHub Copilot. Built for agentic coding, long-running tasks, and knowledge work. Give it a try today! https://t.co/CkQzmZUVPS https://t.co/b66z7s00qs

Media from the original post
♡ 827 likes↻ 82 reposts↳ 21 replies
Collected original
ClaudeGitHub Copilotv5.5VideoExternal link
View original post on X ↗
Coding & agents𝕏

🏃🏽‍♂️‍Agent Merge: Keep Your PR Moving in VS Code Discover Agent Merge (Experimental) in VS Code, a powerful way to keep your pull requests moving after they’re open. Let the agent handle review comments, failed checks, and merge conflicts, apply the necessary fixes, rerun builds and tests, and keep working until your PR is ready to merge. ➡️ https://t.co/9nQZZJ6SlP

Media from the original post
♡ 133 likes↻ 14 reposts↳ 14 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

📣 @OpenAIDevs's GPT-6 family is expanding in GitHub Copilot with two additional models now generally available. ☀️ GPT-6 Sol: the balanced model for interactive and agentic coding. 🌕 GPT-6 Luna: a lightweight, cost-efficient model for smaller tasks and the lowest-cost option in the family. Try them in the GitHub Copilot app or @code. https://t.co/gyEGwnYxFT

♡ 403 likes↻ 31 reposts↳ 17 replies
Collected original
GitHub CopilotOpenAIv6
View original post on X ↗
Coding & agents𝕏

Try them out today in Devin Desktop and Devin CLI: https://t.co/y3humFMnN0

♡ 20 likes↻ 0 reposts↳ 0 replies
Collected original
DevinThreadExternal link
View original post on X ↗
Coding & agents𝕏

GPT-6 Sol and Luna are now available in Devin. On FrontierCode 1.1, GPT-6 Sol matches GPT-5.6 Sol’s score at 61% lower cost per task. GPT-6 Luna scores above GPT-5.6 Luna at about a quarter of the cost. At under $0.10 per task, it is the cheapest model on the leaderboard. https://t.co/Mct0ZGxMO2

Media from the original post
♡ 751 likes↻ 57 reposts↳ 55 replies
Collected original
DevinOpenAIv5.6v6
View original post on X ↗
Coding & agents𝕏

In our evaluations, we see that GPT-6 Sol reads about 17% less context than GPT-5.6 Sol to reach the same score, and rarely leaves a repo with failing tests after its last edit. GPT-6 Luna’s biggest gains are at low and medium reasoning effort, where it writes real regression tests instead of mock-based ones. Read more: https://t.co/2pz6g4Agux

♡ 53 likes↻ 0 reposts↳ 3 replies
Collected original
OpenAIv5.6v6Thread
View original post on X ↗
Coding & agents𝕏

GPT-6 Sol and GPT-6 Luna are available in the API and rolling out in Codex and ChatGPT Work for Plus, Pro, Business, and Enterprise users. https://t.co/fv2OS3jEI3

♡ 180 likes↻ 8 reposts↳ 5 replies
Collected original
OpenAIv6ThreadExternal link
View original post on X ↗
Coding & agents𝕏

GPT-6 Sol and GPT-6 Luna build on Astra’s alignment advances, showing improvements over the GPT-5.6 Sol and GPT-5.6 Luna models in our alignment evaluations. https://t.co/zdJfhce2O0

♡ 174 likes↻ 4 reposts↳ 4 replies
Collected original
OpenAIv5.6v6Thread
View original post on X ↗
Coding & agents𝕏

GPT-6 Sol and Luna just landed in Astra’s orbit. Both launch today with API prices 50% lower than GPT-5.6. Build with Sol. Scale with Luna. To production and beyond. https://t.co/ZCEFp4JdjV

Media from the original post
♡ 9.6K likes↻ 750 reposts↳ 277 replies
Collected original
OpenAIv5.6v6Video
View original post on X ↗
Coding & agents𝕏

On FrontierCode 1.1, our benchmark for real-world engineering tasks that grades mergeability and quality, Opus 5.5 scores 65.3% on Extended — taking the leading spot from Fable 5 at a fraction of the cost. Read more: https://t.co/ELoIAbeica

♡ 21 likes↻ 1 reposts↳ 1 replies
Collected original
ThreadExternal link
View original post on X ↗
Coding & agents𝕏

Try it in Devin Desktop and Devin CLI: https://t.co/y3humFMnN0

♡ 11 likes↻ 0 reposts↳ 1 replies
Collected original
DevinThreadExternal link
View original post on X ↗
Coding & agents𝕏

Claude Opus 5.5 is now available in Devin. On FrontierCode 1.1, Opus 5.5 takes the #1 sport from Fable 5 at a fraction of the cost. https://t.co/QUhqpGjO9X

Media from the original post
♡ 586 likes↻ 35 reposts↳ 44 replies
Collected original
ClaudeDevinv5.5
View original post on X ↗
Coding & agents𝕏

🚀 @AnthropicAI's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and @code. https://t.co/tt9Pf4wAmv

Media from the original post
♡ 375 likes↻ 44 reposts↳ 40 replies
Collected original
ClaudeGitHub Copilotv5.5Video
View original post on X ↗
Coding & agents𝕏

Claude Opus 5.5 is now available in Cursor! It's the new top model on CursorBench at 57.8% (Max) and costs 40% less per task than Opus 5. https://t.co/TMeNqjClCo

Media from the original post
♡ 4.7K likes↻ 199 reposts↳ 269 replies
Collected original
ClaudeCursorv5.5
View original post on X ↗
Coding & agents𝕏

The fastest PDF-to-Markdown parser just got faster. ⚡️ With LiteParse v2.14.6, text-based PDFs parse about 25% faster. Across realistic documents, LiteParse processed pages at 2.8ms/page and 1.5× faster than the next-fastest local parser. LiteParse is open source and runs locally in Python, Node.js, Rust, or directly in the browser. Grab v2.14.6 → https://t.co/UJy6KQ1Dyi Bench Docs → https://t.co/rVY3Cxyj8H

Media from the original post
♡ 68 likes↻ 1 reposts↳ 12 replies
Collected original
v2.14.6
View original post on X ↗
Coding & agents𝕏

Formatting code is SO much easier with the Prettier extension ✨ #vscodeextensions #prettier https://t.co/ijZz9g0RyY

Media from the original post
♡ 300 likes↻ 28 reposts↳ 7 replies
Collected original
Video
View original post on X ↗
Coding & agents𝕏

See how surgeon @pridgenmd uses Codex to build his own tools and review scientific literature on PubMed: https://t.co/i8cs5FikTw

Media from the original post
♡ 406 likes↻ 28 reposts↳ 29 replies
Collected original
OpenAIVideo
View original post on X ↗

September 21, 2026

Coding & agents𝕏

Build with Grok 4.7 and Vercel for less. 40% off until September 27th on AI Gateway. Try with @v0, @eve, and fx. https://t.co/mYLO5Gesx6

♡ 420 likes↻ 34 reposts↳ 50 replies
Collected original
v0External link
View original post on X ↗
Coding & agents𝕏

@latentspacepod @allenpark out now wherever fine podcasts are sold! (email, apple podcasts, youtube) https://t.co/AMwZCJ5IEK

♡ 12 likes↻ 0 reposts↳ 13 replies
Collected original
Thread
View original post on X ↗