Suraj

I agree.

[zeus @thecatzeus3]

ai saved me three hours. i used them to ask it if it was sure.

[Herrington Darkholme @hd_nvim]

-----BEGIN RSA PRIVATE KEY-----
4
-----END RSA PRIVATE KEY-----

[Gergely Orosz @GergelyOrosz]

How on earth did this happen:

The Indian certificate authority (CA) eMudhra had one job (well, two):

1. Create secure, 384-bit private keys
2. Store these securely and do not leak them

Well, eMudhra chose private keys between 1 and 256 (the numbers!!) and called it a day. WTF

[Noah @noah_bino]

Spent 3 weeks building a texting app slower than email. Messages fly at pigeon speed — LA to NYC takes 22 hrs. Sometimes the bird dies & the message isn’t delivered.

[Wise @trikcode]

I haven't seen a C++ vibecoder yet.
I wonder why?

[Larry the Cat @Number10cat]

Politicians come and go, cats remain.

[Larry the Cat @Number10cat]

"Whether Starmer stays or goes we can all agree that me being fed is the most important thing"

[himanshu @himanshustwts]

Based on everything explored in the source code, here's the full technical recipe behind Claude Code's memory architecture:

[shared by claude code]

Claude Code’s memory system is actually insanely well-designed. It isn't like “store everything” but constrained, structured and self-healing memory.

The architecture is doing a few very non-obvious things:

> Memory = index, not storage
+ MEMORY.md is always loaded, but it’s just pointers (~150 chars/line)
+ actual knowledge lives outside, fetched only when needed

> 3-layer design (bandwidth aware)
+ index (always)
+ topic files (on-demand)
+ transcripts (never read, only grep’d)

> Strict write discipline
+ write to file → then update index
+ never dump content into the index
+ prevents entropy / context pollution

> Background “memory rewriting” (autoDream)
+ merges, dedupes, removes contradictions
+ converts vague → absolute
+ aggressively prunes
+ memory is continuously edited, not appended

> Staleness is first-class
+ if memory ≠ reality → memory is wrong
+ code-derived facts are never stored
+ index is forcibly truncated

> Isolation matters
+ consolidation runs in a forked subagent
+ limited tools → prevents corruption of main context

> Retrieval is skeptical, not blind
+ memory is a hint, not truth
+ model must verify before using

> What they don’t store is the real insight
+ no debugging logs, no code structure, no PR history
+ if it’s derivable, don’t persist it

[Larsen Cundric @larsencc]

The gap between "works in a demo" and "works at scale" is about 4,000 commits.

[Wholesome Side of 𝕏 @itsme_urstruly]

Bro pulled off the best video of his life

[Antidepressant Content @depressionlesss]

God's most beautiful creation

[Om Patel @om_patel5]

stop spending money on Claude Code.

Chipotle's support bot is free:

[james hawkins @james406]

Marcus Aurelius wrote this over 1800 years ago:

"the secret to peace is 10xing your productivity with AI agents and custom Claude skills. you must escape the permanent underclass. buy my course"

[Gergely Orosz @GergelyOrosz]

Saying not knowing how to code gives you an advantage in building software (thanks to AI) is like saying not knowing anything about filmmaking gives you an advantage in making films (thanks to having a smartphone + apps to edit stuff)

Ignore this stuff and keep learning+building

[Andrej Karpathy @karpathy]

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.

Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.

As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.

It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

[Gergely Orosz @GergelyOrosz]

If you pay attention he said AI will write all the code (which is happening at Anthropic) and never said they won’t need software engineers.

Turns out software engineers prompting the AI results in much better software, and software engineering is a lot more than writing code!

[Home of Fight @Home_of_Fight]

⚡️Demetrious Johnson goes OFF on fans criticizing Khamzat Chimaev’s performance at #UFC319

"If you guys don’t wanna watch grappling and wrestling — don’t watch the UFC.

You guys are complaining about something which is very easy problem to fix.

Let’s say Khamzat is about to fight again. All you have to do is, you see this button right here. It’s called off button, [presses remote].

It’s a very simple problem to fix guys. You making it a bigger deal than it is."

🎥 @MightyMouse

[Piotr Mazurek @ SGLang Summit @tugot17]

I solved every single problem in the CUDA mode book. A quick thread summarizing this experience and what I learned 1/x

[Kane 謝凱堯 @kane]

I wonder if these PMs know and hate each other in real life

[Suraj @surajhande]

Wonder how may of these are going to be featured on https://t.co/XYdu1LPCun down the line.
#GoogleIO