agentic

6.1K posts

agentic banner
agentic

agentic

@itsagentic

Founder @IntentYou | Building at @CrucibleLabs Writing about agentic AI, programming, React, UI/UX, and shipping real products

Buenos Aires Katılım Kasım 2012
444 Takip Edilen2.1K Takipçiler
Sabitlenmiş Tweet
agentic
agentic@itsagentic·
I care less about AI demos and more about whether the tool helps people ship. I write about: • agentic AI in real workflows • programming and React • UI/UX • founder lessons from building products If it reduces dropped context, improves handoffs, and helps teams move faster, I am interested.
English
1
0
4
181
agentic
agentic@itsagentic·
@vercel agentic ftp is finally here
English
0
0
0
71
agentic retweetledi
Melkey
Melkey@MelkeyDev·
Ralph Loops Loops Graphs guys stop lol just send your prompts and stop listening to online people
English
24
11
157
5.9K
agustina
agustina@aguusmood·
Banco totalmente. Como vamos a festejar quedar segundos? eso dejenlo para selecciones chicas. Ya cuando salieron a festejar q le ganamos a cabo verde y egipto me dió vergüenza ajena
Español
2
2
13
3.8K
Guillermo Rauch
Guillermo Rauch@rauchg·
The big lesson from AI is that everything is code. A slide deck is code. Design is code. That cool promo video? Code. Excel automation? Code. The universe? Probably made of code too.
English
412
505
5.4K
237.1K
agentic
agentic@itsagentic·
@rauchg open models getting this good at defensive security is a big deal
English
0
0
0
422
Guillermo Rauch
Guillermo Rauch@rauchg·
Based on internal evals: ▪️ Kimi K3 is top-tier at cybersecurity There is chatter on X that Moonshot benchmark-overfit. These are stealth evals. Model has raw IQ. ▪️ Sol is a leap ahead in cyber capability At a significantly higher cost, but quite remarkable still. ▪️ Fable refuses everything We couldn’t get it to complete the run at all. What’s interesting is that Sol in comparison was much more open to helping with defensive cyber hardening TL;DR: frontier, open-weight cybersecurity capability is here. Try it on deepsec.sh for defensive purposes.
Malte Ubl@cramforce

We ran Kimi K3 on a private cybersecurity benchmark. TL;DR: Kimi K3 is the workhorse for cyber security tasks at great recall/precision/price. GPT 5.6 is best recall/precision but at 7x higher cost per run. For context, Deepsec.sh is an open-source cyber harness designed for finding vulnerabilities in large codebases. The eval runs deepsec on an undisclosed open-core application at a git sha before a large number of security issues were fixed. This is a secret eval that cannot be directly benchmark-maxxed. S-Tier: GPT 5.6 Sol: By far the most thorough analysis, but coming in at over 7x the price of the runner up. Best price/recall: Kimi K3. Next tier of recall at a good price Best price at good recall: GLM 5.2 (40% lower price than Kimi K3) GPT 5.5: Only recommended with subscription or high-discount API price. Similar recall to Kimi at much higher list price. Opus 4.8: Only recommended with subscription or high-discount API price. Similar recall to GLM 5.2 at much higher list price. Fable 5: 100% refusal rate. Cannot be used for security analysis. Sol on a large code base will quickly get into 6-figure pricing. This is still affordable relative to the risk of letting security issues unfixed or paying bug bounties. I'd recommend using Sol for a one-time baseline and then using Kimi K3 for continuous analysis. When using open-weight models, make sure to use an inference vendor that supports zero data retention.

English
145
300
4.5K
1.1M
elvis
elvis@omarsar0·
Sharing my new skill! It keeps track of high-signal X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: #x-mcp-%E2%80%94-x-api" target="_blank" rel="nofollow noopener">docs.x.com/tools/mcp#x-mc… 2. Install skill here: github.com/dair-ai/dair-a… 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: academy.dair.ai/dashboard/reso… I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.
English
44
73
771
68.1K
agentic
agentic@itsagentic·
@charliermarsh great work, this is one of those changes you feel immediately
English
0
0
1
17
Charlie Marsh
Charlie Marsh@charliermarsh·
Next Codex release gets incremental rendering for streamed Markdown in the TUI, hundreds of times faster for large outputs
Charlie Marsh tweet media
English
23
11
431
18.9K
Jon
Jon@jonvolio·
arrêtez d'utiliser LUCIDE ICONS please surtout quand il y a ces bangers dispos 👇 → Phosphor (le duotone 🤌) → Iconoir → Tabler → Solar → Hugeicons et le cheat code pour toutes les utiliser avec 1 seul plugin, tree-shaking inclus unplug-icons sur gh
Français
15
14
270
21.6K
agentic
agentic@itsagentic·
@steipete loops for execution, graphs for explaining why it got stuck
English
0
0
0
10
Juan Cruz
Juan Cruz@DevJuanCruz·
a que edad te enteraste que los captchas son para entrenar a la IA a detectar imagenes
Juan Cruz tweet media
Español
4
0
16
1.1K
shadcn
shadcn@shadcn·
Kimi's developer console uses shadcn/ui.
Indonesia
81
30
3K
110.2K
agentic
agentic@itsagentic·
@swyx this is what agent automations are actually good at
English
0
0
0
60
swyx
swyx@swyx·
btw if you havent set your {codex | claude | gemini | devin} automations to autoresearch how to improve your seo/aeo every week you are really truly missing out on free, should-be-commoditizing-but-weirdly-untapped alpha
English
102
47
2.1K
164.6K
agentic
agentic@itsagentic·
framework devtools should answer one question before anything else: where did the time go? everything after that is decoration.
English
0
0
1
23
shadcn
shadcn@shadcn·
React Aria is now available in shadcn/ui. Use `--base aria` or choose React Aria in shadcn/create. All components, docs, CLI, styles and skills have been updated for React Aria Components. Shoutout to @devongovett who did most of the work behind this release.
shadcn tweet media
English
98
112
2.1K
149.4K