
AI engineer @futurestandard_ · agent systems + LLM pipelines in prod · learning inference engineering in public · OSS: AgentBudget, SnapShell
Bengaluru
Joined October 2023
- Tweets333
- Following565
- Followers60
- Likes2.9K
macOS won't let an app take Cmd-H, even after you move Hide to other keys in App Shortcuts. Got a fix for that merged into @yab_browser today. It finds Hide by its action instead of its title, so it works for Yab, Yab Dev and localized menus.
github.com/yetanotherbrowser…
1
40
And we got out first contribution in lessgoooo !!!
Replying to @yab_browser
@yab_browser seems promising
github.com/yetanotherbrowser… here is my little contribution @korablev. Would love to contribute more so that i can learn quality engineering :)
Looking at this gives me a checkpoint on where did I start and what did I learn across these.
More work to be done going ahead !
3
54
Got a small fix merged into x-md today. Two of its MCP tools were failing on any post without a language tag, hit it while wiring it into an agent. If your agent needs to read X posts, it turns them into compact Markdown with no X API key.
github.com/pc-style/x-md
@pcstyle53 Kudos
1
3
150
checkout mdfromx.com for the full fun !
Point you agents towards the docs page and ur agent to self serve it
With all the hotchpotch of API key leaks and compromises, I made this github.com/KTS-o7/keyturn
This is to rotate and revoke things faster.
Do check it out
An urgent notice from the Railway team
blog.railway.com/p/security-…
The irksome experience of using ride hauling apps like @Uber
1. A cabbie accepts the ride when he is 5kms away in another ride. Calls and asks not to cancel. After finishing his ride he cancels anyways.
2. Even after quoting around 35-45rs per km to travel on ORR no accepts
Why the transport in Bangalore is so broken ? @krishnabgowda @Tejasvi_Surya when will we get good public transport instead of bitti bhagya?
Why should I be paying predatory prices for pathetic facilities?
Krishnatejaswi S retweeted
kivi for Mac is here.
Typing is officially optional on your Mac.
Talk in any app, and kivi turns what you say into clean, ready-to-send text. No more typing out long emails, messages or prompts.
Here's everything kivi can do 🧵
🤖 Made with AI
The amount of short form content that is being consumed while driving an auto or a cab is insane and scary
Almost no attention to road and causing scary experiences :)
1
19
444
It feels really dejecting to know that only thing standing between us and accomplishments areGPUs.
we will find some workaround
Personally a thing that I do to manage this is to think of small experiments to learn the same concepts at small scale.
Mostly cope but works i guess
There’s a peculiar helplessness in watching the world race ahead in AI while being unable to participate at the frontier because of constraints completely outside one’s control.
5
183
So this means
Lower usage for the same amount of money.
Now anthropic has Avenue to reduce usage.
All model companies are tending towards stopping subsidized rates and we will pay API costs.
Good old times are getting over folks.
Hi,
Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.
Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.
(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.
(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.
(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.
(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.
I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.
Codexingly,
Tibo
6
275
This city has a planning and administration problem. No funds for development and drains the soul to live and work like this.
Sigh
5
62
Just open-sourced my tax filing playbook 🇮🇳📄
A checklist + AI skill prompt + strategy guide for India's new tax regime. No fluff, just the steps I used this year.
Feel free to use any LLM and follow along for a hassle free ITR filing !
github.com/KTS-o7/personal-p…
AI infra day - @adarshxs from @huggingface was a great host. @SarvamAI s engineers gave a wonderful insight on how to approach hosting and serving models at scale. @tokenbender had a really cool topic but unfortunately I couldn’t grasp it much. Overall a productive day !
















