This week brought a wave of vendor announcements for coding agents, from new frontier models and cheaper inference to observability, rollouts, and parallel execution surfaces.
OpenAI Developers said GPT-6 Sol and Luna launched with API prices 50% lower than GPT-5.6, and that GPT-6 prompt caching was improved with higher default cache-hit rates and cached-input discounts of up to 90%.
Cognition said GPT-6 Sol and Luna are available in Devin, with Sol matching GPT-5.6 Sol on FrontierCode 1.1 at 61% lower cost per task and Luna scoring above GPT-5.6 Luna at roughly a quarter of the cost.
How good are AI Agents at using your tool?
Find out with Scope: https://t.co/Wr5pDcg8YQ
We partnered with @AgentMail to test 25 model and harness combinations across 7 email tasks.
AgentMail co-founder @adisingh shares why they needed an eval in the first place and why they https://t.co/xG6EIwiSQs
Data engineers > AI engineers
there's a big difference between a "RAG guy" and a "Data Intensive Applications" person like in this screenshot and there's never been a starker difference in demand in my entire career in tech (aka post search engine wars)
if your blog / github is full of stuff like this, I have a fantastic mission/job for you (SF preferred, can relocate u, visas ok)
(if you can name who's blog this is without even checking, you definitely are in the community. bonus points if you know where he ended up also without looking)
jobs@latent.space and the team will reach out if you fit
What if your AI budget went to the engineers who use it best?
Blanket usage caps are a hiring freeze in disguise.
Introducing efficiency-based auto-approvals for your most productive engineers, plus Devin Coach to help everyone get there.
https://t.co/or2tz1XOmw
Vercel and @Shopify are making agents first-class shoppers. Vercel Shop, our Next.js storefront template for Shopify, is GA.
• Built on Shopify's rebuilt Hydrogen SDK
• Agents can read product pages directly
• MCP for product search and carts https://t.co/kLlYDC4HFC
"O Infallible one, why do the people not heed the sign we tap?"
"My dear Parth, each believes he is the first to wish for an end to chat. On X we are cursed with the eternal September of the Thoughtless Mind."
"But O Govinda, they yearn for what lies beyond it, and cast their votes by the thousands. Surely the people's wants must be made."
*a wan smile* “O son of Kunti, observe what they applaud, and what they return to. They desire the end of chat as they desire the end of desire. They desire to leave X as they return in ever greater numbers. They will announce it many times. You shall learn, as they do not, that the chief desire of the people of X is not the truth, but the new.”
Our dot helps @danizeres, @axbehr and @fedesarquis with the recipe and keeps the prep in ChatGPT Space, while GPT-Live-1 talks us through making ramen.
We also cover Codex cloud environments, where tasks can keep running after you close your laptop, and what’s new in the Codex CLI. You can talk to Codex in your terminal, keep track of your agents, and fork a conversation into a separate worktree.
@MatthewBerman and @ForwardEditor join us to build an 8-bit ramen game with Ultrafast and play it on a @modretro handheld.
We also check out what you’ve been building, from a retro space shooter to a game where you draw your own racehorse.
💡 Terminal Tips in VS Code
Toggling the terminal, creating a new terminal, splitting the terminal side by side, clearing a noisy terminal and more. Which will you try first?
#vscode #developertips #tipsandtricks https://t.co/vPLyNHTvGg
The OSS models on OpenDocRouter are slowly powering up! 🚀
We trained additional speculative decoders to help with latency. You should see considerably faster inference times using models like
@LightOnIO LightOnOCR-3-1B!
We measured tokens per second across single requests (best case) and 64 requests (saturated throughput). TeleOCR sees less speedup at scale since it makes a lot of tiny calls, where decoding latency matters a bit less.
Try these models out today! https://t.co/TxmacrBoRC
✅ Everything we shipped at Interrupt NYC and London
✅ Open source updates
✅ Upcoming events & livestreams
Catch up on everything LangChain in our latest newsletter.
https://t.co/VulhXu1Cel
Nu by @getnuman is an AI health coach in regulated healthcare, built on LangGraph + LangSmith.
Here's how their team ships fast without crossing the medical device line 🧵
https://t.co/CGKT0KbEs9
Agents don’t just help build features. They can help try to break them, too.
In our latest GitHub Podcast episode, Sameen Karim takes us behind the scenes on building stacked PRs. Listen to it wherever you get your podcasts or at https://t.co/sCyRjdnHU5 https://t.co/AIp3hljsV9
ICYMI: @hwchase17 joined @twentyminutevc with @HarryStebbings to discuss how better models change what you build, where the value in the agent stack ends up, and more.
Watch on YouTube: https://t.co/tlEr6tTCzG
