Software Engineer

Prague
Joined April 2014
Viliam Elischer retweeted
Instead of .md specs, try this: make the system a state machine (or rather, a reducer). Ask your slopus to make an interactive diagram with real events from your flow and the real reducer. Step through them, asking the agent "whys" this and that.
38
98
14
1,889
112,685
Viliam Elischer retweeted
How do always-on, proactive agents like @Bot work? Watch my lecture at Stanford CS146S: 2:35 How we got here 6:13 What changed in the models 10:06 Inside an always-on agent 18:07 The harness 27:26 Context engineering 34:26 Where this is going
183
465
115
4,632
806,642
Viliam Elischer retweeted
opentunnel - public urls for anything running on your machine tunnel services exist but this one is different - e2e encrypted, relay can't see shit - sdk to embed this functionality in your apps will be integrated into opencode tomorrow
121
148
27
3,289
140,723
Viliam Elischer retweeted
Excalidraw CLI released! Log in to your Excalidraw+ account or use with local files. You can easily render Excalidraw diagrams to give better output feedback to your agents. Install today.
48
97
25
1,481
73,261
Viliam Elischer retweeted
Introducing pocketty_ SSH for iPhone & iPad, made for herdr~! 🎉 🔸 Get notified when an agent on any host is blocked 🔹 Tap → you're in that exact pane 🔸 Supports Tailscale/Bonjour natively 🔹 Diffs for every agent turn 🔸 No account or subscription pocketty.app/?utm_source=x&u…
9
11
1
43
5,186
Viliam Elischer retweeted
Codex 🤝 Tailscale Codex Cloud can now securely connect to resources on your tailnet with Tailscale. Useful tools should be easy to build with, combine, and turn into something even more useful. See how it works → buff.ly/yFcldrC
156
442
154
5,195
1,228,849
Viliam Elischer retweeted
BREAKING: The U.S. government, Google, Meta & Zuckerberg-backed @biohub are launching a $1.8B push to build the data layer for AI biology. The goal is to create the largest open, AI-ready biological dataset ever assembled, giving models the data needed to better predict how biology works & ultimately help treat disease. The coalition is massive: › Biohub committed $500M › DOE is investing $500M+ across measurement, modeling & compute › NIH is bringing $500M+ of federally funded datasets & repositories › Meta, Google DeepMind & @IsomorphicLabs are jointly investing another $300M This is effectively an infrastructure buildout for AI biology. Instead of just building bigger models, they’re attacking one of the biggest bottlenecks in biology AI today, generating standardized, high-quality biological data at massive scale & making it openly available to researchers. $1.8B committed to turning biology into something AI can increasingly model, predict & engineer.
144
523
117
4,136
1,822,932
Viliam Elischer retweeted
If you work with graph data structures (you should), I built a seriously powerful open-source graph library for you: @statelyai/graph - Plain JSON graphs - Convert DOT, Mermaid, GraphML + more - So many algorithms - Visual + structural graph props - Fully type-safe + FAST github.com/statelyai/graph
16
53
1
568
22,725
Viliam Elischer retweeted
One little trick to make your codebase more readable: * Install cccc github.com/moznion/cccc * Configure it with max-cognitize and max-cyclomatic 40 * In AGENTS.md, instruct to validate that cccc passes * Have one agent in ultracode refactor everything until cccc passes 🤩
16
23
1
440
51,273
Viliam Elischer retweeted
Claude now works inside Google Docs, Sheets, and Slides, and those files also open inside Claude. In Google Workspace, Claude sits in a sidebar next to your file, reads what you have open, and edits it in place. You can approve each edit before it lands.
854
4,304
2,068
54,370
13,328,289
Viliam Elischer retweeted
We just released Polars 2.0. It removed many of our legacy decisions makes the streaming engine our default and promotes SQL to a first class citizen within Polars. It comes with initial out-of-core (spill to disk) support, a new Map data type and a lot of performance improvements. In fact, we think Polars is now one of the fastest analytical SQL engines on a single node. See benchmarks in the post: pola.rs/posts/release-polars…
16
157
23
1,266
90,673
Viliam Elischer retweeted
mattpocock/skills v1.3 is out! - /pr (new) writes easy-to-read PR bodies, showing hard evidence that the changes work and assessing merge risk - /implement-spec (new) takes in a spec and tickets, and implements them with subagents - CONTEXT.md renamed to GLOSSARY.md - /retro (new) reviews recent coding agent sessions and suggests repo improvements /retro, especially, feels like a huge upgrade. Enjoy!
143
255
42
3,490
332,819
Viliam Elischer retweeted
Ok, `/retro` by @mattpocockuk is a game changer. Turns out my agents are bumping into all kinds of problems that went undetected, but due to agentic cleverness and persistence, the features still got built one way or another. Now I can restart from a reliable foundation.
23
27
3
989
71,980
Viliam Elischer retweeted
I mixed Jev + an espresso (state) machine. Turns out, Jev's a pretty good barista ☕ Introducing Jevspresso: XState determines what's possible, Jev decides the next move. Order in plain language, or break stuff and watch Jev cope. Try it: jevspresso.dev
31
36
4
504
33,282
Viliam Elischer retweeted
Impressive. And scary.
Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).
Readers added context they thought people might want to know
The 48% figure and "video Turing test" claim are from Tavus's own study of 54 one-minute calls, not independently verified or using a standard protocol. Griffin-Lite leads NVIDIA's VideoFDB benchmark on their public leaderboard. cellcog.ai/blog/tavus-gri… research.nvidia.com/labs/amri/proj… tech-ish.com/2026/10/02/tav…
32
69
10
1,477
467,075
Viliam Elischer retweeted
Effect feels insanely good to use with agents: - Typed errors/dependencies power up your type checking - DI makes designing good codebases easy - Built-ins for EVERYTHING, no agent creativity required An outrageous advantage for any non-frontend TS code
Effect v4 is here. One ecosystem. Zero dependencies. The next chapter of Effect and the foundation for building reliable software and AI agents in TypeScript.
73
83
7
1,703
176,429
Viliam Elischer retweeted
NousCon 2026 October 30th, NYC luma.com/y0y9ngkm
218
140
62
2,557
841,957
Viliam Elischer retweeted
Introducing "cf", an agentic CLI for the entire Cloudflare API. You can do nearly anything. Even buying a domain is incredibly simple from the CLI. Don't know what command you need? Run `cf cli search "look at messages stuck in my queue"` and it will return a list of relevant commands. blog.cloudflare.com/cloudfla…
186
236
87
3,620
181,513
Viliam Elischer retweeted
Introducing Forge, a pluggable, open-source pipeline that runs in CI to generate SDKs, CLIs, and documentation directly from API definitions. By shifting generation upstream into individual team repositories, Forge keeps developer tools continuously in sync. cfl.re/4jsqgSY #BirthdayWeek
30
86
15
1,046
61,404