CommandCode.ai
@commandcode.ai
3 months ago A dollar for $40 of DeepSeek V4 Pro usage?
Hard to say no to that.
💬 0
♻️ 0
❤️ 0
A dollar for $40 of DeepSeek V4 Pro usage?
Hard to say no to that. “The wave will pass. The products will be quietly deprecated or repositioned. The companies that survive this cycle will be the ones who figured out how to offer compute as a capability that developers tap into, not as a place they move into.”
pepicrft.me/blog/sell-co... The completed systematic review can be found at the link below. elicit.com/review/55ee... Below is a recap of the notable features we discussed:
- Run multiple searches and combine results.
- Verify decision making.
- Import full text with chrome extension.
- Extract data from tables and figures.
- Generate report with citations.
- Enable dual reviews.
- Leverage Elicit APIs. The full walkthrough of Elicit Systematic Review is now live.
During the session, we ran a complete review from start to finish in 60 minutes while highlighting the cool new features that really made this feat possible.
Try out your protocol at elicit.com.
www.youtube.com/watch?v=MdM... Heads up for Nuxt users: The Nuxt team disclosed four CVEs yesterday, including a route middleware bypass.
Upgrade to nuxt 3.21.6 or 4.4.6 as soon as possible. Full breakdown of impact on Netlify deployments in the changelog.
www.netlify.com/changelog/20... Try Terminal Threads now in Zed v1.3.5:
zed.dev/releases/sta... Read more about Terminal Threads in our latest blog post:
zed.dev/blog/termina... This is especially useful for Claude Code users. With upcoming changes to their pricing, Terminal Threads will be the only way to use Claude Code in Zed with your existing subscription.
Open a new Terminal Thread from the Agent Panel and your terminal session appears in the sidebar. Use them for cli agents, long compiles, eval runs, or anything you want to keep visible and organized in your workspace.
Terminal Threads are live in Zed v1.3.5! You can now run claude, amp, pi, or any terminal-based workflow as a managed thread in the Threads Sidebar, right next to your other agent threads.
Magicare migrated to PlanetScale and achieved an 85%+ reduction in query latency, 17× faster materialized view refreshes, and a 6× smaller database footprint per instance. Read the article for all the details.
/plan now takes a task inline.
Reads your code before it writes any.
Outputs the plan as a file.
Edit it. Then run it.
Execution is the easy part. vibe coding without understanding what's going on feels like I'm a child whose parent took over my school project I don't feel good when I'm done, and I sure won't be able to answer any questions in show 'n' tell tomorrow
Google's Gemini 3.5 Flash is now live in Netlify AI Gateway. Zero config required.
Call it from your Functions with the Google GenAI SDK. No API keys, no auth setup. Caching and rate limiting are handled for you.
www.netlify.com/changelog/ge... I fear AI models might be somewhat veblen goods, and that we all somewhat conflate price with quality
New in v0.26.11
Command Code supports Gemini 3.5 Flash.
Pro-level coding, parallel agentic execution, 1M token context.
Live in /model, same hour Google shipped it. "Stop and Think" was (is?) probably the most repeated idiom at the camp, preceding the cartoon side note: if you have a son approaching ages 12-16 I wholeheartedly recommend Camp Pasquaney!
first time I've licensed a cartoon! this particular cartoon was pinned to the bulletin board outside the dining hall at the summer camp I went to and worked at for eight summers, and as far as I know it's still there
Slow Mode
blog.val.town/slow-mode If you’re not careful, ingress (free) can become egress (not free). Double-check your agents work, they could quietly be costing you money.