Ranga Reddy (@irangareddy) header
Ranga Reddy (@irangareddy) profile picture

tuning agents to build software. 2x  apple ssc winner. sih ‘19 finalist.

San Francisco, CA
Joined February 2020
Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)Photo by Ranga Reddy (@irangareddy)
Built wishper, your free alternative Wispr Flow Download now, Stop Typing and Start Speaking. free · open-source · on-device · mlx powered wishper.irangareddy.in/
3
10
1,171
Now, I call this “no ball dropping” 😂
23
May be I saw 4th post on free disk space
41
agree, most of our growth has come with @thsottiaux ship 28 days(944 PRs). grateful for resets, and today is also big day we got 170+ users. towards self evolving codebases. stack now: - @claudeai for planning and steering - code gen and review: @ChatGPT codex - agent runtime: @orca_build (this month experimenting) - monitoring: @sentry and @posthog
Our super duper lean engineering team went from shipping 226 to 1,460 PRs a month. We didnt hire more, but just built out the validation system to run this at scale. Here's our stack: Code gen: @conductor_build / @cursor_ai Review: @greptile PR merges: @spurtest Regression: @spurtest Ship fast only works if you can trust what you ship
1
2
144
Today, I realized how a growth team that truly knows the game can bring value and validate a product in ways no testing software can.
56
In the race of people building extensive connectors, Google has everything at its fingertips
New in Gemini: Connect Google Wallet for personal finance insights This is powerful for things like: + making instant charts to visualize your spend + finding sneaky subscription price hikes + making a holiday budget based on what you actually spent last year
40
The gap between the expert and everyone else is closing. With the new models, you can see "no" diminishing for swe's
58
unfortunately this ends up being somewhat of a random process some companies are able to grow aggressively like Meta and raise money and refuse to give up anything nvidia had a more challenging path so i imagine that resulted in a weaker board
41
are your deployment today done by
75%agent
25%human
4 votes • Final results
46
so much to learn from mark zuckerberg
52
TIL: every email we sent to “Hide My Email” users was bouncing. Apple only relays mail from domains you register under Services → Sign in with Apple for Email Communication. I missed adding those. our backend quietly stopped emailing those users, so nobody noticed. audit caught this, fixed in 2 mins with claude :)
77
Btw. I can not unsee Claude slides
SuperMimic has won the CORL’s best paper award. Thanks for everyone’s support!
4
205
attention and taste
PSA: creating wonderful products still requires extraordinary amounts of human focus, effort, motivation, and love. And an attention span.
1
53
does anyone in my timeline follows weekly releases of software products apps, and any such. what you're learning after claude, codex maxxing
1
2
107
this is what happens when you truly want system act on immediately, good ship @vercel
So bullish on MCP. Its utility exceeds the "M" part: even AI aside, it'll be a civilization-scale accomplishment to get all our systems communicating through one universal open protocol. A missing piece was how to get arbitrary callbacks across sessions. MCP could read and write, but it couldn't tell you later "this event happened." MCP Events fixes this. We're adding support in our own MCP. Say an agent makes a deployment, and wants to know when it's complete. Instead of polling, it can subscribe to 𝚍𝚎𝚙𝚕𝚘𝚢𝚖𝚎𝚗𝚝.𝚜𝚞𝚌𝚌𝚎𝚎𝚍𝚎𝚍. PSA: With Vercel Queues and Workflows, writing the backend machinery for your own MCPs to do this is easy peasy.
48
got 3 👀
Replying to @ClaudeDevs
We're giving Ultra and Team Premium users Fable resets based on how long you've subscribed: <6 mo: 1 6–12 mo: 2 >12 mo: 3 Use them anytime by March 8. Pro and Team Standard get a week to try Fable 5.2, up to half your weekly limit, plus one reset. support.claude.com/en/articl…
2
54
/goal automate workflow agents orchestrations: teapawt.org/ryaneshea/status/21187… agent harness: teapawt.org/joelniklaus/status/211…
I burned a shitload of compute so you don't have to. Releasing the Harness Leaderboard. Which harness should you run your open model in? I ran 28,849 trials to find out. The leaderboard compares nine coding-agent harnesses on open models. In each comparison only the harness changes: the model, provider and reasoning effort stay fixed, and every task gets three attempts. The trials ran GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint on Terminal-Bench 2.1 and DeepSWE, for $4,746 of inference. Averaged over the three models, mini-swe-agent (@KLieret), a bash-only agent, solves 51.4% of tasks and @openclaw 27.3%. Four others are statistically tied with mini-swe-agent. One of them is Pi (@pidotdev), at 49.4% for $0.29 per solved task, about 45% less than mini-swe-agent's $0.53. The best harness depends on the model: mini-swe-agent on GLM-5.3-Flash, Hermes Agent (@NousResearch) on DeepSeek-V4.1-Flash and Kimi Code (@Kimi_Moonshot) on Flint. @opencode costs $3.35 per solved task, 11.7 times as much as Pi. See Harness Hub's Harness Lens for what the nine harnesses do differently. It documents the prompts, tools and compaction of 34 coding-agent harnesses and links every claim to its source. Leaderboard: huggingface.co/spaces/joelni… Harness Lens: huggingface.co/spaces/harnes…
49
ci/cd costs are growing faster as agentic coding increases commit and pr frequency, triggering more builds, tests, and deployments. going back to first principles: identify redundant runs, optimize caching, run only affected tests, and reduce unnecessary compute without compromising reliability. building a tool for small teams to analyze ci/cd workflows and cut costs. my weekend is locked. will mostly find a better skill for all repos we have backend api, iOS, Android, and Web(React) or create one.
5
2
158
one thing that caught my eye this week is teapawt.org/ShopifyEng/status/2118…
We rebuilt our mobile apps in Swift and Kotlin with agents. To keep pace and hold our quality bar, we built Reflex: an agentic-first architecture that lets agents build and verify app behavior across iOS and Android without needing devices or simulators. Here's how it works, piece by piece: shopify.engineering/reflex
18
Ranga Reddy retweeted
Apple's Core AI models repo is now accepting third-party contributions 🥳 If you have developed some cool ports, this is the best place to share your recipes with the community. Looking at you @JackdeS11 @mattt @kevinqz 😂 github.com/apple/coreai-mode…
10
32
4
276
12,961