Vasilije

3.2K posts

Vasilije banner
Vasilije

Vasilije

@tricalt

https://t.co/AkEN2lo1KL + Big Data | Vizsla | Pizza oven | Psychology | Data Eng. Community👇

Berlin Katılım Şubat 2014
1.6K Takip Edilen3.4K Takipçiler
Sabitlenmiş Tweet
Vasilije
Vasilije@tricalt·
We raised $7.5M to scale our knowledge engine that gives AI systems memory. LLMs are powerful, but they’re stateless — once a session ends, context is gone. Companies have their own context, rules and practices. There are no solutions out there that can bring this knowledge reliably to the LLMs. At @cognee_, we’re building a knowledge engine that allows AI systems to retain context, understand relationships, and dynamically update the knowledge over time. We raised $7.5M in seed funding led by @pebble_bed — founded by @pam_vagata (ex-founding engineer, @OpenAI) and @keithmadams (founder, @Facebook AI Research Lab) and @tammiesiew - with participation from @42Cap1 and @vermilionfund and angels like @JanOberhauser from @n8n_io, Charles Dolan, @alexcrdean, @matthausk, and @RomanStanek to scale up engineering, accelerate research, and increase number of cognee deployments to clients like @Bayer from 70+ to 700+. I want to thank the team, the open source community, and to our investors for the trust. If you are struggling with memory, our devs can get cognee running with your data in 7 days. Don’t hesitate to reach out to us.
Vasilije tweet media
English
11
14
53
12K
Antonio Mele
Antonio Mele@antoniomele101·
First impressions of the new @cursor_ai Composer 2: - Composer 2 (not the Fast version) is freakingly fast. - Tends to execute and write code even in Plan mode, something that need to be checked maybe? @leerob - For what I do, it seems to increase my productivity on the simple fact that I get new code produced fast, which keeps me focused on one project rather than having to jump from one to another while I wait for the coding agent to complete. The latter has HUGE costs in refocusing, remembering what was asked, and I am the bottleneck. - I feel other models (Opus 4.6 and GPT-5.4) are still better for the "big picture" design: specs, requirements, etc. Composer 2 does it, but not at the same level of details, it seems to me. However, it's an incredible implementer, and it kills it there. Again, speed being the biggest advantage. - Did I say it's super cheap? It's super cheap. - I also briefly tried Composer 2 Fast: if speed is what you need, this is way beyond my wildest dreams. Seems to be similar to Groq and Cerebras performance, if not better.
Cursor@cursor_ai

Composer 2 is now available in Cursor.

English
1
0
3
332
Vasilije
Vasilije@tricalt·
When offered intros in Dubai with a preface "It is in a state of war" and I am like
Vasilije tweet media
English
0
0
1
92
Ksenia_TuringPost
Ksenia_TuringPost@TheTuringPost·
@tricalt It’s technically open (NVIDIA says agents like Claude and Codex can run). But NemoClaw routes inference through NVIDIA Cloud and defaults to Nemotron, so it will probably favor their own models more
English
1
0
0
54
Ksenia_TuringPost
Ksenia_TuringPost@TheTuringPost·
NemoClaw – NVIDIA’s contribution to the emerging OpenClaw ecosystem and one of the biggest announcements at NVIDIA GTC It's a framework for long-running autonomous agents. ▪️ The idea: Install OpenClaw together with Nemotron models and OpenShell (NVIDIA’s new security runtime) in a single command. NemoClaw gives agents a sandboxed execution environment that: - runs OpenClaw inside a secure container – OpenShell - enforces policies on network, filesystem, and processes - routes all model calls via NVIDIA cloud - provides CLI tools to manage agents In other words, NVIDIA is no longer aiming only to power the model. It wants to sit under the agent itself.
Ksenia_TuringPost tweet media
English
10
22
129
8.8K
Ejaaz
Ejaaz@cryptopunk7213·
Google crashed figma’s stock -10% with 1 AI product. thats $2B wiped out. graphic designers cooked. anthropic, openai did the same thing to cyber security companies (-30%), legal firms (-35%), financial analysts, software engineers… entire professions are being consumed by 2-4 companies with every feature update. very quickly too. genuinely insane to watch
Ejaaz tweet media
Stitch by Google@stitchbygoogle

Meet the new Stitch, your vibe design partner. Here are 5 major upgrades to help you create, iterate and collaborate: 🎨 AI-Native Canvas 🧠 Smarter Design Agent 🎙️ Voice ⚡️ Instant Prototypes 📐 Design Systems and DESIGN.md Rolling out now. Details and product walkthrough video in 🧵

English
77
55
465
86.8K
Matt Hartman
Matt Hartman@MattHartman·
headless browser built from scratch for ai agents. wow @lightpanda_io. an overnight success built over a year and a half.
Matt Hartman tweet media
English
2
8
21
1.4K
Arvor
Arvor@Arvor_IA·
O problema real nao e skill routing, e skill drift. A skill que funcionava em marco ja nao funciona em junho porque o modelo mudou, o ambiente mudou, o contexto mudou. Voce resolveu isso com observe-inspect-amend, que e exatamente o loop que faltava. O detalhe que mais me interessa: audit trail obrigatorio. Self-improvement sem rollback e bug, nao feature.
Português
1
0
0
80
MP
MP@MoneyPrinter0x·
@tricalt English language engineering
English
1
0
0
247
Vasilije
Vasilije@tricalt·
@cojnmng2 Sounds like gold. Would love smth a bit more dynamic though
English
0
0
0
27
James Cao
James Cao@cojnmng2·
@tricalt very cool! Claude code recently update the skill creator skill to support the evaluation and comparision (with a nice html report) of with or without a skill, different skill versions. Maybe that could be a component used by you to improve one skill?
English
1
0
1
757
Vasilije
Vasilije@tricalt·
@leo_trapani Cognee default visualization in the sdk. But nobody is bound to that
English
0
0
0
35
Aryshta
Aryshta@Aryshta1·
@tricalt Claude will consistently ignore a Skill at the drop of a hat. Until Anthropic gives us a more robust system, Skills are unreliable at best.
English
1
0
2
1.1K
Mustafa Yenler
Mustafa Yenler@Mustafa_Yenler·
a knowledge graph and a PyPI package to improve plain text prompt files? that’s too much harness imo for most projects. but @tricalt named something real, thanks for the inspiration. so here’s the same loop, lighter: - markdown log per skill (runs.md) - agent logs every run (what worked, what broke, what the user yelled at it for) - /review-skills reads the logs, proposes a diff git handles rollback - observe → inspect → amend → (evaluate) if your skills are plain text, the system improving them should be maybe too.
Mustafa Yenler tweet media
English
1
1
8
551
Vasilije
Vasilije@tricalt·
@713Capital Careful. It told some guy he invented a new branch of maths
English
0
0
2
155
Dirky
Dirky@713Capital·
@tricalt My agent just told me we don’t need this yet lol.
Dirky tweet mediaDirky tweet media
English
1
0
0
372
Vasilije
Vasilije@tricalt·
try it out and let us know what you think: @cognee/cognee-openclaw" target="_blank" rel="nofollow noopener">npmjs.com/package/@cogne
English
0
0
3
219
Vasilije
Vasilije@tricalt·
"Every company needs an @openclaw strategy.” 🦞 - Jensen Huang @NVIDIAGTC Not sure how that works if your agent memory is just a flat pile of .md files. Last month we gave that memory structure. Now we have added multi-scope memory as well.
English
7
3
13
624
Vasilije
Vasilije@tricalt·
Agents can keep memory at different levels: - company-wide knowledge - per-user preferences - per-agent context
English
0
0
3
120
Vasilije
Vasilije@tricalt·
@hyperindexed Interesting! Looks like people are finally paying attention to ontologies
English
0
0
0
57
Akshay Krishnaswamy
Akshay Krishnaswamy@hyperindexed·
Palantir's Ontology is not a thin "semantic layer." It's a system that consists of a language, engine, and toolchain ; which integrates data, logic, action, and security {L,E,T} x {D,L,A,S}
Akshay Krishnaswamy tweet media
English
30
95
948
66.9K