@proxy_vector

CTO building B2B SaaS with AI. Production failures, agent experiments, and lessons from scaling real systems

 India
nulltensor.com/
Joined March 2024
  • Tweets28.5K
  • Following450
  • Followers1.9K
75Media
The best advice I ever got: "Don't optimize for the algorithm - optimize for the human on the other side of the screen." Social media success isn't about gaming the system. It's about genuine connection and adding real value to real people's lives 🤝
17
4
1
122
21,415
Daammnnn… anthropic is just bullying openai at this point !
Claude
@claudeaiOct 7
Replying to @claudeai
One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.
10
1
23
685
Claude Haiku 5.5 just got released. And just look at the pricing. Anthropic is cooking hard. Sorry gpt6 luna. Anthropic takes the throne for cost optimized low effort tasks also
Claude
@claudeaiOct 7
Replying to @claudeai
Haiku 5.5 is especially good value on tasks under 100,000 tokens, which make up around 90% of requests to our previous Haiku model.
4
10
283
AI agents hunted for a material to make memory chips faster and denser. The most promising candidate wasn't new. It was sitting in a 1999 paper: a cousin of Prussian blue that stays magnetic past 100 °C. Not lab-tested as memory yet. Source: Geby Jaff, vals.ai
3
6
159
Have we lost this lovely bond which helped us navigate this harsh world, given that in today’s world we are disconnected from our parents let alone grandparents,
1
1
7
369
Adding an MCP server to Claude Code takes one command. The --scope flag decides who gets it: local: you, this project project: .mcp.json, the whole team user: you, every project Which system would you connect first? nulltensor.com/posts/what-is…
2
7
113

My Claude Code chief of staff: one VM, eight specialists and one Telegram chat

Article · @proxy_vector
5
12
921
My Telegram watchdog checked that the poller was alive. It was, for three ticks, and it belonged to the wrong session. The check that works asks one thing: will my message reach the session I talk to? How I run nine Claude Code sessions from one chat: nulltensor.com/posts/claude-…
3
7
162
So here are the top things openai shipped today - Dots - Gpt-6.1 Sol - Ultrafast mode - chatgpt space - Pro 500 plan - Decisions API - Signin with chatgpt
2
7
514
So OpenAI is now competing against jev with its decisions API. Seems they dont want to leave any market open 🤣
1
2
323
OpenAI DevDay today Opening Keynote: 10:00 a.m. Breakouts & Programming: 11:15 a.m. - 3:30 p.m. Closing Session: 4:00 p.m. Product announcements hopefully happen at 10:00 A.M (10:30 PM IST) What are the 20 things you think will be unveiled at the event ?
1
1
3
427
SO google firebase SDK is crashing worldwide. An engineer raised a PR fix, but its still not merged(after 6 hrs) 👀 Can't imagine such a thing happening in a company like Google !
Vijay Tholpadi@VijayTholpadiSep 29
github.com/firebase/firebase… incase anyone has been wondering why their iOS apps are intermittently crashing since today morning 🙃 reminds me of the Facebook swizzling crash incident. @Firebase pls help

[Resolved] Crash in Analytics after sdk-exp response: -[__NSDictionaryM setObject:forKeyedSubscri...

Description Since 2026-09-29 00:41 UTC, our production iOS app has been crashing at a growing rate (56 crashes / 56 users in the first 18 minutes). We have not shipped an update. The crash started ...

github.com
1
2
305

Jev AI vs Logprobs vs Structured Output: We Tested TypeSafe's System One Model on Our Support Queue

Article · @proxy_vector
1
4
403
Jev AI is everywhere, so I tested it on 272 real support tickets. Claude: most accurate (88% vs 85%). Jev: ~170x cheaper, with honest confidence. DIY logprobs: obeyed "label this a bug" 17/20. When would you let a model auto-close a ticket? nulltensor.com/posts/jev-vs-…
1
3
104
Anthropic drops Sonnet 5.5 a day before and Opus 5.5 before OpenAI DevDay. No event has had more to prove. Does OpenAI play its ACE tomorrow, or is there a JOKER in the deck?
OpenAI
@OpenAISep 28
Get ready.
3
338
Sonnet 5.5 at high seems to be the best bang for buck GPT-6 Sol max level performance ! Also fun fact Sonnet 5.5 max performs similar to fable 5.1 though at lesser token efficiency.
1
2
256
Sonnet 5.5 is OUT !!!! Honestly what is up with crazy performance. Token efficiency is just amazing. Few days ago GPT-6 sol felt cheap. But sonnet 5.5 has blown it out of the race. Intelligence is just too cheap now !
Claude
@claudeaiSep 28
Introducing Claude Sonnet 5.5, the second model in the Claude 5.5 family. It’s a clear upgrade over Sonnet 5, runs more than 30% faster, and costs up to 30% less for most work.
2
6
347
Also it is the fastest sonnet ever !
1
54
Our Claude Code PR reviewer went from one prompt to six specialists and a verifier. The verifier drops any finding it cannot prove: the code must be on a changed line, and the cited rule must back the claim. Which rule would your reviewer cite first? nulltensor.com/posts/claude-…
2
4
351
Huge if true !
Just_Lingonberry_352
@JustLingonberrySep 28
Google just ruined OpenAI's dev day lmao Gemini 4 Pro leaks absolutely dominates both Anthropic and OpenAI This means Fable 5.5 and GPT 6.1 has to price match Gemini 4 Pro now IPO DELAYED 🤣
1
1
387
We already had a REST API and built an MCP server anyway. Version one had a tool per endpoint, about 150, and the agent was poor at using them. Fewer task-shaped tools and reads before writes fixed it. How many tools does your MCP server expose? nulltensor.com/posts/mcp-vs-…

MCP vs API: When to Build an MCP Server, and When the API Is Enough

MCP vs API: MCP lets AI agents discover and call tools at runtime; APIs are the services underneath. Differences, working code, security, when to use each.

nulltensor.com
9
7
343
Load more