Prateek Gogia 💭 retweeted
Introducing /sickday
It writes your leave request.
Your agent keeps shipping.
You do missions in Vice City.
Sus timing? Your manager deserves atleast this much.
Prateek Gogia 💭 retweeted
We’re making a personalized cancer vaccine for Yash, a 34 year-old pancreatic cancer patient, in the open with his consent.
We want external experts to review our design and make their own contributions before we manufacture it at the RNA Foundry.
RNAFoundry.com/yash
Prateek Gogia 💭 retweeted
A few weeks ago I rewrote an entire Node app in Go. 28mb binary, almost instantaneous builds + deployment.
If we aren't manually typing code, what is the point of developer-friendly languages? Why not write everything in Go, or even C++?
Prateek Gogia 💭 retweeted
There is still no substitute for caring. Every piece of software getting rapidly better is happening because a human cares. And happens to be using AI to move really fast.
hot take: you don't need a software factory, and i don't love the term. it's just marketing
all you need is good software engineering and investing your tokens in the right places. the more deterministic the better (and token efficient)
LFM3 from @liquidai is on Ollama! Small models built to run anywhere and fine-tune on a single GPU:
- Text, vision, audio, omni, and decision models
- Text model fits in about 1 GB at 4-bit
- 256K context window
Available to run locally.
Prateek Gogia 💭 retweeted
+ "you know what i'd really like?"
- "tell me"
+ "a website"
- "...we can do a website"
+ "a real website, not some claude generated neon slop, a real website"
- "i'll make you a very good traditional handmade website, one that is built with dozens of snippets from stackoverflow"
Prateek Gogia 💭 retweeted
A very interesting video, that young ppl who have just started working or doing decent in their carrier should take note of youtu.be/IL4vR1wwH5M?si=hHhB…
Prateek Gogia 💭 retweeted
The Unleash The Avatar team is soon going to the Himalayas in December to finish the last of our 3D scanning for assets. It finally ends our cross country asset scanning trip.
Photoscanned assets (which we spend a lot of time optimizing) are gorgeous, and I can't wait to show you how much we leveled up again when we launch the next trailer!
Prateek Gogia 💭 retweeted
Anthropic, every few months:
Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems.
This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution.
The emerging rules of thumb:
→ Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions.
→ Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data.
→ Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with.
The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed.
Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up.
As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete.
claude.com/resources/article…
Prateek Gogia 💭 retweeted
when the cybersecurity team finds out there are actual vulnerabilities and they have to do their jobs instead of trying to trick someone into clicking a phishing email
Prateek Gogia 💭 retweeted
There's nothing to "fear monger". Everyone big in the industry has revoked the 8 intermediate certificates already.
Mozilla has permanently removed emSign Root CA G3 from its software. Google will remove it permanently too in the next few days.
Reputation damage is done. The world has mostly "fixed" this mess eMudhra has created and has permanently stopped using one of the very few Indian Certificate Authorities trusted globally.
Replying to @GoI_MeitY
However, some social media accounts are indulging in fear mongering about the impact of this incident. The facts of the case are as follows:
eMudhra operates in two distinct areas:
Readers added context they thought people might want to know
This is not fear-mongering. This has been validated by security professionals across the world which could have impacted almost every individual on the internet.
blog.mozilla.org/security/2026/…
arstechnica.com/security/2026/…
en.wikipedia.org/wiki/EMudhra#2…
🔐 Node.js security updates are now available!
New releases for Node.js 22.x, 24.x & 26.x address multiple vulnerabilities, including high-severity issues.
Review the details and update your systems to stay secure.
🔗 nodejs.org/en/blog/vulnerabi…
#NodeJS #Security
Prateek Gogia 💭 retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/DeepI…
1/4

































