Full-stack guy here with a little 🤏 knack for design. What I do: Code and yapp in meetings.
terminal
Joined August 2021
- Tweets2K
- Following236
- Followers127
- Likes1.7K
fyi
Yesterday, while I was working throughout the day, I noticed that my daily Codex session limit was draining faster than usual. At the end of the day, it struck me that in the morning I enabled the tab completion flag in T3 Code. Once I disabled that, it started working as usual. Sessions are no longer draining faster.
6
Watches Ramayana: Part 1 today, and first time in my life did I truly experienced how Dangerous Ravana actually was, the true meaning of Dasha nan. 💀
Btw banger movie definately recommend.
This is a side side side project, but look at this monstrosity, guess which model did this.
It was my fault to even look at the diff.
1
17
At this point, self-AI review reveals some strange review comments, which are possible, but the possibility is just ridiculous.
1
15
A bumper offer is going on right now in the s/w industry, new model, new and a higher number of vulnerabilities found.
"When the company ran diagnostics on about 700 systems, it found 10,500 vulnerabilities and held an emergency press conference on June 16, applying fixes over three months.
However, when it re-ran diagnostics using "GPT-6 Astra," the latest model released by US-based OpenAI, it confirmed 35,000 new vulnerabilities. "Honestly, we're completely exhausted" finance.biggo.com/news/2cb8f…
30
Anthropic's pricing policy on Phone vs Web is the opposite of what you usually see.
They charge INR 1999/m on mobile phones and INR ~2400/m on the web (both inclusive of tax).
For Claude PRO.
19
Dear Cristiano, people from outside Portugal loved you as dearly or more than your own countrymen did.
suiiii 🖤 🐐
2
53
How clever of Devin. When I first saw this, I was confused. Did I already disable training before?
10
Hey, can anyone from the GH CLI team look into this issue? It's marked as blocked for now.
@github
github.com/cli/cli/issues/14…
21
Someone should compare these news agencies' video footage and pictures because ANI's quality is down the drain.
37
Started with
Tabnine → gh copilot → supermaven 🤯 → cursor tab
Back then, coding was fun the feeling of moving fast, with what you were thinking being a tab away, was so f-ing awesome.
38
Here we go again, google benxhmaxed prev versions so hard it's just isn't possible to look at these numbers without side eyeing.
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
16
