silentsilverr

217 posts

silentsilverr banner
silentsilverr

silentsilverr

@silentsilverr

SDE @Google

Bangalore, India Katılım Ocak 2025
349 Takip Edilen21 Takipçiler
silentsilverr
silentsilverr@silentsilverr·
I am looking for an app developer with experience in Flutter for my brother's startup. Interested people, please reach out for more information.
English
8
0
3
215
silentsilverr
silentsilverr@silentsilverr·
Dude, what's up with Bangalore's weather? That was the only good thing about it, and now it's gone!
silentsilverr tweet media
English
0
0
0
39
silentsilverr
silentsilverr@silentsilverr·
Coding jobs won't disappear, but coding itself will be taken out of some jobs.
English
0
0
1
22
baba yaga
baba yaga@S_N_SH_E_·
Need A review on this playlist
baba yaga tweet media
English
61
3
156
13.4K
Srajan
Srajan@_Creation22·
I am never applying again 🙏
Srajan tweet media
English
120
16
850
243.2K
silentsilverr
silentsilverr@silentsilverr·
Restaurant owner: We need something different to beat this crunching competition. Head chef: Say no more...
silentsilverr tweet media
English
0
0
0
39
Master Muskan
Master Muskan@MasterMuskan22·
I am just a fan of this guy, he's SDE2 @Flipkart but still attend all the contests. Unreal consistency, GOAT!!
Master Muskan tweet media
English
19
4
328
10.4K
silentsilverr
silentsilverr@silentsilverr·
@AtharvaXDevs I'd totally pay for internet to see more posts like this. Congrats! :D
English
0
0
0
55
Anshika Aggarwal
Anshika Aggarwal@kipupwidanshika·
Here was my bangalore expense during 2 month of internship Pg: 12.5k Food: 6k(I just couldn't eat PG food) Travel: 2k in auto, cabs Outings: 2k(didn't go out a lot) Misc: 1-2k Total: 26k around Bangalore is expensive because of the rent and sometimes travel or else you can get good food easily in less amount. It's as per you how you would like to spend.
English
22
6
153
18.6K
silentsilverr
silentsilverr@silentsilverr·
Everyone's using AI these days, but how Google's putting it into their stuff is wild!
Google@Google

Today @GoogleMaps is getting its biggest upgrade in over a decade. By combining our Gemini models with a deep understanding of the world, Maps now unlocks entirely new possibilities for how you navigate and explore. Here’s what you need to know 🧵

English
0
0
0
23
silentsilverr retweetledi
Google Maps
Google Maps@googlemaps·
Finally, you can ask Maps to “Find me a public toilet nearby where I don’t need to wait in line to buy something." Welcome to the future.
English
631
1.6K
28.5K
4.3M
divyansh
divyansh@Divyansh91565·
Problem was so hard ngl that I finished an entire packet in one sitting… just thinking about it 😔
divyansh tweet media
English
5
1
44
1.4K
silentsilverr
silentsilverr@silentsilverr·
Our brain constantly reminds us for a behaviour to get a reward. But our brain only cares about the reward. So, we can smartly change the behaviour to develop good habits.
English
0
0
0
28
silentsilverr
silentsilverr@silentsilverr·
People overestimate what they can do in a day and underestimate what they can do in a year
English
0
0
0
30
silentsilverr
silentsilverr@silentsilverr·
Winners and losers have the same goals but different systems. Spend time building systems not chasing goals.
English
0
0
0
23
silentsilverr
silentsilverr@silentsilverr·
@HelloVyom Sorry to break it to you, but there are ways to export a conversation between an LLM and you. So technically, you won't have a true first interaction.
English
0
0
0
9
VG🌪️
VG🌪️@HelloVyom·
Everyone is obsessed with bigger models and larger context windows. But the real bottleneck for agents is memory. LLMs are fundamentally stateless. They do not remember users, prior interactions, preferences, or outcomes across sessions. Every new interaction starts from zero. Most teams try to patch this with vector databases, but flattening everything into embeddings loses structure, time, and causality. As systems grow, retrieval gets noisy and agents stop improving. If agents cannot remember users, outcomes, and past decisions, they will always behave like it is the first interaction. HydraDB is building the context layer that actually makes agents stateful so they can persist context, learn from outcomes, and get better over time. Excited to see this launch.
Nishkarsh@contextkingceo

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built @hydra_db for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️

English
19
6
40
3.3K