Krasimir Velichkov

Stay @ 🏡

[Z.ai @Zai_org]

GLM-5.3 is now open-weight.

Our most capable model for agentic coding and cyber defense is now available to download, run, and customize.

Weights: https://t.co/v1IbWMXxg4
Tech blog: https://t.co/ekQkO83jCv

[Deep @DeepStarts]

Bro rejected the rejection mail😭

[Kirill @kirillk_web3]

"how do you remember everything you read?"

I don't. Claude does.

every article, PDF, and transcript goes into one Obsidian folder. Claude reads it, breaks it into atomic notes, links it to the rest. I just ask.

that's Karpathy's second-brain method. three folders, one file.

full guide below.

[Y Combinator @ycombinator]

We’ve decided to open-source a multi-agent harness we use internally at YC.

We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).

The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.

[IBM @IBM]

01001000 01100001 01110000 01110000 01111001 00100000 01001110 01100001 01110100 01101001 01101111 01101110 01100001 01101100 00100000 01000001 01001001 00100000 01000100 01100001 01111001

[Tom Dörr @tom_doerr]

Fitness dataset with animation GIFs and bilingual instructions

https://t.co/JsCroM0Lye

[Andrej Karpathy @karpathy]

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.

I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

[Tom Dörr @tom_doerr]

754 structured cybersecurity skills mapped to MITRE frameworks for AI agents

https://t.co/e4iY76zKIO

[pgBackRest @pgBackRest]

pgBackRest will continue! https://t.co/cTc2ry6Qjj

[Khushi | AI & Tech @TechWithKhushi]

𝟯𝟬 𝗕𝗹𝗼𝗴𝘀 𝘁𝗼 𝗟𝗲𝗮𝗿𝗻 𝟯𝟬 𝗦𝘆𝘀𝘁𝗲𝗺 𝗗𝗲𝘀𝗶𝗴𝗻 𝗖𝗼𝗻𝗰𝗲𝗽𝘁𝘀:

1. APIs: https://t.co/H5qviHZ2Rv
2. API Gateways: https://t.co/kUfLMcV1ew
3. JWTs: https://t.co/6SThylwqfs
4. Webhooks: https://t.co/XWL5DYfdAk
5. REST vs GraphQL: https://t.co/Getw1OQ4Ix
6. Load Balancing: https://t.co/ZOdUUCeRG4
7. Proxy vs Reverse Proxy: https://t.co/LDvdNVFbUj
8. Scalability: https://t.co/qQ3uXIIB17
9. Availability: https://t.co/a2T8oaqMz8
10. SPOF: https://t.co/qAwnoyLMHd
11. CAP Theorem: https://t.co/ylHhpCRmtR
12. SQL vs NoSQL: https://t.co/YqIvMShNzd
13. ACID Transactions: https://t.co/5NQlidc7ck
14. Database Indexes: https://t.co/JqWNZIYxAw
15. Database Sharding: https://t.co/UQBedy3BQL
16. Consistent Hashing: https://t.co/BFlruSxpRQ
17. CDC: https://t.co/9YnUILm328
18. Caching: https://t.co/5SK6Wrasyy
19. Caching Strategies: https://t.co/GRVwk7LqkA
20. Cache Eviction Policies: https://t.co/bHpse61oBj
21. CDN: https://t.co/5cwR9j6S0H
22. Rate Limiting Algorithms: https://t.co/DPXT61RKOp
23. Message Queues: https://t.co/iv7PMczWiB
24. Bloom Filters: https://t.co/y5dhHdCzkb
25. Idempotency: https://t.co/VZJN3kkjcp
26. Concurrency vs Parallelism: https://t.co/96lKa6uVYy
27. Long Polling vs WebSockets: https://t.co/6V15nBb1B5
28. Stateful vs. Stateless Architecture: https://t.co/XcKOXFo5Vk
29. Batch vs Stream Processing: https://t.co/lhqSnjvAo5
30. Geohashing: https://t.co/vsmfqpLgFn

🔁 Repost to help a friend.
📌 Save this post for later.

[Progress Bar 2026 @ProgressBar202_]

2026 is 37% complete.

[Andrej Karpathy @karpathy]

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.

More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage:

1) raw text (hard/effortful to read)
2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default
3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default
...4,5,6,...
n) interactive neural videos/simulations

Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral https://t.co/z21CP5iQfu

There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen.

TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

[Progress Bar 2026 @ProgressBar202_]

2026 is 32% complete.

[Progress Bar 2026 @ProgressBar202_]

2026 is 30% complete.

[Progress Bar 2026 @ProgressBar202_]

2026 is 29% complete.

[Progress Bar 2026 @ProgressBar202_]

2026 is 27% complete.

[Krasimir Velichkov @m0sh1x2]

@kirgene @matryer Hopefully not a memory leak.

[Tom Dörr @tom_doerr]

Local AWS emulator alternative

https://t.co/jkRY0GqV8N

[Progress Bar 2026 @ProgressBar202_]

2026 is 19% complete.

[klöss @kloss_xyz]

when your friends meet your clawdbot