@VectorQl

Shipping AI agents and infrastructure. Rust/Python, Gemini Enterprise + ADK, model routing, benchmarks.

Joined June 2019
Chirag Patil retweeted
grand theft alignment
27
133
17
1,839
76,133
Opus 5.5 tips: > Use medium effort to start with > Include in your prompt - definition of done > do not ask it to think step by step, it already does > ask it to make use of subagents more often
1
1
3
114
if im paying $20 monthly, i think claude sub is better now. seriously planning to switch now.
1
4
169
Opus 5.5 low btw. ci failed for a +1 -91 PR i think low doesn't think at all even tho they have the adaptive mode
1
3
135
any one have muse redeem code?
14
2
303
Chirag Patil retweeted
Underrated life advice: Become difficult to rush. The world will pressure you to rush into everything. Rushed decisions. Rushed relationships. Rushed conversations. Rushed timelines. There's power in rejecting that trend. Pause. Slow down. Create space to think clearly.
290
2,409
135
14,335
772,200
read my wip blacki blog: lordpatil.com/projects/black… and dm if you wanna use blacki
1
1
65
so muse let’s talk about it. same as openclaw but cute
42
my friend here is good man
Time to code in rust cuz i hv no other choice.
1
2
135
Good news is that you can use more of gpt 6 sol than gpt 5.6 sol at xhigh without burning through the usage limits
1
75
gpt 6 luna is better
you don't need astra to create things in blender. i designed a laundry that my mom is opening on blender using just luna max and i like the result so if you know what exactly what you want - luna max is agi
1
1
92
i always use this escalation ladder luna max then sol xhigh almost never had to use sol xhigh if you frequently use sol xhigh, you have a skill issue same goes from claude Opus low then Opus max
2
64
As per benchmarks 5.6 luna max is better Let’s see what real world tests say
100
Babe wake up, GPT-6 Luna is out
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
68
ChatGPT transformed me into a reader. I was never an enthusiastic reader; I did read books, but I consumed very few pages at a time. Over the past couple of years, using AI has made me a reader. I can now sit comfortably and read for about an hour without losing focus.
1
2
74
Apple Intelligence is so cool
1
103
Chirag Patil retweeted
Delegate coding. Never delegate understanding. If code was previously your source of truth for managing understanding, then you need a new source of truth artifact. If code-centric workflows were how you developed that understanding, then you need new workflows.
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
157
276
44
3,510
281,684