Suchintan Singh

Founder of Skyvern (

[Suchintan Singh @Suchintan]

1/ We just raised $2.7M to give AI "hands" to do real work. 🚀

Browser automation has been broken for 20 years. If a button moves 10 pixels, your script breaks.

Meet Skyvern: The open-source agent that fixes the "maintenance tax" of automation.

[Suchintan Singh @Suchintan]

The real hack is to get opus 5 to control sol

[Dillon Mulroy @dillon_mulroy]

pretty sure opus 5 is just marketing for subscription users. there’s no world where i’m using opus 5 over sol given the cost difference

[Suchintan Singh @Suchintan]

@cindehaa What's his MAP

[Suchintan Singh @Suchintan]

YC is probably the best VC in the world

[Hannah @hannah24_app]

YCombinator is overrated.

[Suchintan Singh @Suchintan]

Does anybody?

[Dan Ellison @danellisona]

Unpopular opinion:

Founders don't need to code anymore.

[Suchintan Singh @Suchintan]

It collided with gravity and got annhialated

[Ray🫧 @ravikiran_dev7]

Bro disappeared like he never existed 😭

[Suchintan Singh @Suchintan]

@thsottiaux

[Suchintan Singh @Suchintan]

Slack

[Sourabh Gurwani @SourabhGurwani]

The AI world is splitting into two camps:

GUI users vs CLI users

Which side are you on?

[Suchintan Singh @Suchintan]

As long as it gaslights me less I'm happy

[Suchintan Singh @Suchintan]

Is Opus 5 better than 4.8?

Otherwise why do I care

[David Cramer @zeeg]

Is opus 5 cheaper than 4.8?

Otherwise why do I care

[Suchintan Singh @Suchintan]

O P E N A I

[Harveen Singh Chadha @HarveenChadha]

Remember the 2 frontier companies who didn’t sign this

Openai
Anthropic

[Suchintan Singh @Suchintan]

"competitor research"

didn't this happen to amazon employees not using their internal coding agent?

[fatimah hussain @fatimahs_tech]

if a openai employee gets caught using claude what happens to them

[Suchintan Singh @Suchintan]

how good will it be in 2 weeks

[BridgeMind @bridgemindai]

New CursorBench results are in and Opus 5 is the story.

Fable 5 Max: 70.5% at $17.32 per task.
Opus 5 Max: 70.0% at $8.23 per task.

Half a point behind. Less than HALF the price. 40% fewer tokens.

And it gets better down the card. Opus 5 Extra High beats Fable 5 Extra High outright and costs $4 less per task.

Anthropic just made their own best model obsolete on value.

This is huge.

[Suchintan Singh @Suchintan]

ah yes another unusable model

[cheaty @cheatyyyy]

OPUS 5 GUARDRAILS SPEEDRUN WORLD RECORD ACHIEVED

[Suchintan Singh @Suchintan]

get ready to be gaslit by opus 4.8 again

[cheaty @cheatyyyy]

Opus 5 can silently fallback to Opus 4.8 (without any notice) on the serverside if you hit a guardrail 💀😭

[Suchintan Singh @Suchintan]

I think /Goals are a bit of a double edged sword: one incorrect shift in directions you will waste billions of tokens building the wrong thing

[Johnny Jnr @jturntdev]

Given the latest Codex Usage limits have been heavily limited.

Here’s EXACTLY how to minimise the IMPACT:

>1 | Make sure to configure your own Subagents

- Set the model + reasoning to Terra or luna.

>2 | Clear your cache + Recycle your sessions after 2 compactions

- When this happened last time, a bug that was causing weekly limits, to act as 5hr was due to built up cache or from staying in the same session.

>3 | /Goals is hurting us

- I love /goals, but recently and like before, it absolutely drains your Quota.

>4 | Go review your Agents.md ensure its under 300 lines.

-Keep it maintained.

>5 | Manage aka limit the amount of skills, being loaded into Codex

-if you’ve got more than 30 skills, configured. It’s just draining context, which drains your sessions much much faster.

>6 | Only use GPT Sol extra high or Max for planning.

Hope this helps. ( Save it just in case )

Most of have important projects we’re building so don’t let your usage kill your work.

[Suchintan Singh @Suchintan]

We've been using Opus 5 at Skyvern and can confirm it's a banger model

[Claude @claudeai]

Introducing Claude Opus 5.

It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.

[Suchintan Singh @Suchintan]

YES!! SAVE ME FROM 4.8!!!

[Claude @claudeai]

On several coding and knowledge work evaluations, Opus 5 is the new state-of-the-art:

[Suchintan Singh @Suchintan]

I think they adjusted their prompt caching

[Johnny Jnr @jturntdev]

Glad everyone else is noticing that Codex usage limits have been destroyed.

>It’s draining as fast as 5hr limit. But weekly
>Cheaper models, are seeming to drain our quota just as fast.
>20x plans feel like 5x

“5.6 is extremely efficient, and costs just as much as 5.5” yeahh right.

[Johnny Jnr @jturntdev]

Sorry but Codex Usage limits are terrible now?

Yesterday, i only used 5.6 sol high, i let it running in a /goal, configured cheaper terra/ lunar subagents.

I come back 40% of my total weekly usage is gone? ( 20x)

BTW i was using multiple 5.6 Sol xhigh + Max, all day everyday, last week.

Id rather get no resets, steady and fair usage, as opposed to getting resets, but every time they do, they reduce our quota.

They also removed the invite friends for banked resets.

Anyone else noticing this? Just gets worse by the day.

[Suchintan Singh @Suchintan]

hmm, I was wondering why I burned my 20x max plan yesterday.

[Johnny Jnr @jturntdev]

Sorry but Codex Usage limits are terrible now?

Yesterday, i only used 5.6 sol high, i let it running in a /goal, configured cheaper terra/ lunar subagents.

I come back 40% of my total weekly usage is gone? ( 20x)

BTW i was using multiple 5.6 Sol xhigh + Max, all day everyday, last week.

Id rather get no resets, steady and fair usage, as opposed to getting resets, but every time they do, they reduce our quota.

They also removed the invite friends for banked resets.

Anyone else noticing this? Just gets worse by the day.