Replying to @devsvn2
github.com/akdevsaha-dev
Follow me on github and access agent skills and more
6
2,878
AI can write code. Getting it to write GOOD code is the hard part.
So I built Factory Skills. It’s simple and easy to understand.
For vibe coders who want to ship better code, and engineers who care about what actually gets shipped.
Skills that make Claude Code, Codex, and other agents understand your codebase, follow existing patterns, and verify their work.
Free. Open source.
agentskill.akdevsaha.com
GitHub: github.com/akdevsaha-dev/fac…
Start with /implement-feature, or try /hungry-jack for larger tasks.
Install:
npx skills add akdevsaha-dev/factory-skills --skill implement-feature
If you find it useful, a star would mean a lot. Feedback and PRs are welcome too.
5
75
Adi retweeted
The lore behind Microsoft’s recent outage
Get ready to see this in your next system design interview lol
Adi retweeted
People still pay 10k for cohorts promising “live sessions, hands on projects and industry mentorship”
Just ask ChatGPT or Claude to teach you with a structured plan. Find project ideas from engineers who regularly share their work here and build them yourself
There’s really no reason to spend 10k on cohorts these days lol
Adi retweeted
Qwen 4 Max preview,
What's with the wheels ? My dear God, physics oriented models need to be in the mainstream. Day by day @ylecun 's world model makes sense to me.
The more a model understands casuality, order, & how physical world works. I'm not a aware of the architecture they have used for this, but most mainstream models are sloppy anyway.
The harness is the one making them do some capable things (that's again is the brain of an engineer making a worst "half baked" product to perform to its fullest potential)
I wasn't aware of Google's game. While everyone was criticizing, Google was building in silence. And now we all see the result. They are shipping things like Madman. Huge congratulations to Google and hopefully I soon recover from Google's dip haha!
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
Adi retweeted
Stop being so cynical about your agents.
Trust them, build, ship and hit that $10K MRR faster
Adi retweeted
If you want to stay on top of the latest tech trends while working, joining a funded startup is probably your best bet
Adi retweeted
Stat always exaggerate things, but Anthropic is the only company where the models have consistent good quality. Unlike some other AI companies.
















