Techylawyer

Legal and IT professional

[Rahul @sairahul1]

Google just dropped a 1-hour course on agentic engineering from scratch:

00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems

This 1-hour watch will replace 10 paid agentic courses on the internet.

Bookmark this. Watch this weekend.

[Martianreturnz/readOnepiece/Spacetime Arc⏳ @martianreturnz]

@QuoteSunTzu The bible

[Daniel Olukoya @REAL_DKOLUKOYA]

By the authority of the name of Jesus, as you say a loud amen, I decree over you:
You will not miss your way. You will not walk into traps. You will hear God clearly and move accurately in Jesus name, amen,
#PropheticFire #MFMPrayers #2026Prophecy #SpiritualWarfare #FaithDeclarations #NewYearPrayer #AmenPower

[Matt Dancho (Business Science) @mdancho84]

Free AI Webinar for Data Scientists

I’m building a real AI system live in Python.

You’ll see how to combine machine learning, LLMs, RAG, agents, and business workflows into one portfolio-worthy project.

Register here (1330+ registered):
https://t.co/3TaJ77moA6

[Artificial Analysis @ArtificialAnlys]

Introducing six new Artificial Analysis Capability Indices for comparing model capabilities across key industry domains

The new industry indices cover Finance & Accounting, Legal, Healthcare & Medical, Strategy & Ops, Engineering, and Economics. We aim to capture the common capabilities required across knowledge work domains and evaluate how well current models meet those needs.

Each index is grounded in common tasks from O*NET occupational classifications. Tasks range from financial modeling, to legal research and contract review, to clinical decision support and patient documentation. We derive capabilities from each task, select the benchmarks that best represent the work, and weight by how often each capability appears across the domain. This means rethinking the Artificial Analysis benchmark suite for each domain and slicing evaluations to relevant domain tasks. Every component benchmark is run independently by Artificial Analysis.

The industry indices join the existing skill-based Agentic and Coding indices, which measure capabilities that cut across every domain.

Key Results
➤ Leading models: Claude Fable 5 (with Opus 4.8 fallback) leads all eight indices, with Claude Opus 4.8 (max) in second on six of eight Capability Indices and GPT-5.5 (xhigh) on two. Below the top two, rankings reshuffle substantially by domain between Gemini 3.5 Flash, Gemini 3.1 Pro Preview, GPT-5.5 (xhigh), Claude Sonnet 5 (max), and GLM-5.2 (max).
➤ Open weights leading models: Among open weights models, GLM-5.2 (max) leads on five of the six industry indices, ranking as high as fifth overall on the Artificial Analysis Engineering Index (53), within 2 points of Claude Sonnet 5 (max, 55) and GPT-5.5 (xhigh, 55). DeepSeek V4 Pro (max, 38) takes the open weights lead on Artificial Analysis Strategy & Ops Index.
➤ Cost efficiency: DeepSeek V4 Flash (max) completes tasks for <$0.04 across all six indices while scoring mid-pack, and GLM-5.2 (max) leads open weights score with a Cost per Task of $0.26 to $0.58. Frontier capability comes at a steep premium: on the Artificial Analysis Strategy & Ops Index, Claude Fable 5 (with Opus 4.8 fallback, $3.48) scores 12 points above DeepSeek V4 Pro (max, $0.03) at over 100x the Cost per Task.
➤ Time per Task: Time per Task spreads roughly 15x within each index, from 1.1 minutes for Nova 2.0 Pro Preview (medium) to 16.7 minutes for Claude Sonnet 5 (max). Speed shows a similar frontier to cost: on the Artificial Analysis Legal Index, Gemini 3.1 Pro Preview (0.8 minutes) completes tasks ~7x faster than Claude Fable 5 (with Opus 4.8 fallback, 5.4 minutes), while scoring within 11 points.

[MFM INT'L HQ YOUTH CHURCH @mfmintlhqyouth]

3 days to go.

The palace has secrets.
The storm has a purpose.
You need to see this.

#Ezanawore
#UnshakenInTheStorm
#3DaysToGo

[Olufemi AWOYEMI @OlufemiAwoyemi]

In closing,

@proshare views the announcement as an encouragement to continue, with the substantive gains still ahead. It affirms the direction Nigeria has taken and confirms that three years of reform are registering with those who allocate capital across borders, though on its own it settles nothing. The value of recognition lies in what follows: first, a reclassification, and then, secondly but harder still, the durable confidence that keeps foreign capital in the market once it arrives.

The work required of the FGN is familiar. They need to keep faith with their own reforms across policy, settlement, access, liquidity, and integrity for long enough for the assessment to resolve in Nigeria's favour and remain resolved.

Nigeria closes the first half of 2026 as one of the stronger equity markets on the continent in dollar terms, with two external reviews still open and a reform record that has begun to command international attention.

The watchlist placement belongs to that record as a real, if provisional, mark of progress. Whether it becomes a reclassification will turn on the evidence Nigeria produces over the coming months, and whether reclassification becomes lasting capital will depend on the discipline the market keeps once the reviews have moved on.

Read more>>> https://t.co/vfrMWTmCtg #EMIU

cc: @NGRPresident @FinMinNigeria @cenbank @ngxgrp @cisnigeria @FMDQGroup @CiiaNigeria @mofinigeria @SECNigeria

[Techylawyer @Techy_Lawyer]

@fishboneOladapo @EMOGY_ @FinPlanKaluAja1 There is work being done to do this, and companies are being incentivised to create the infrastructure. See the extensive work being done on the gas pipelines.

Note, SEPLAT has announced they have stopped routine gas flaring. https://t.co/XPifUZaIuy

[Dan Kornas @DanKornas]

AI agent web search shouldn’t require a paid API key.

ask-search is a self-hosted web search CLI and MCP skill for AI agents, built around SearxNG.

It helps you give local agents searchable web context by routing queries through your own SearxNG instance, then returning clean results for OpenClaw, Claude Code, Antigravity, or any shell workflow.

Key features:

• SearxNG backend – aggregates Google, Bing, DuckDuckGo, Brave, and 70+ more sources through a self-hosted meta-search engine
• CLI-first usage – run ask-search "query" with options for result count, news categories, language filters, URLs-only output, or raw JSON
• Agent integrations – includes an OpenClaw skill, Claude Code CLI usage, and an MCP server for Antigravity / Claude Code setups
• Docker setup path – README includes SearxNG Docker and Docker Compose instructions plus an install script for ask-search
• Real-world fetch notes – documents JSON setup, bot-detection issues, SOCKS proxy options, browser workarounds, and archive-cache fallbacks

It’s open-source (MIT license).

Link in the reply 👇

[Pau Guirao @guirao_pau]

Another cool feature! Buy numbers and use them to call or send sms! Via API or UI

To show you a cool feature I've recorded a video creating a personal assistant which i can call to schedule/handle my meetings!

From nothing to a fully functional agent I can call in just 4 min

Using @zernio and @SpaceXAI apis

[Dan Kornas @DanKornas]

Your AI agent can use a real phone line now — through MCP.

agentphone-mcp is an MCP server that connects AI agents to AgentPhone for phone numbers, SMS, and voice calls from MCP-compatible clients.

It helps you build phone-capable support, sales, or scheduling agents by exposing phone number management, messaging, voice calls, agent setup, webhooks, and usage tools through natural language.

Key features:

• Multiple connection modes – use the hosted Streamable HTTP endpoint, local npx stdio, or a self-hosted HTTP server
• Phone number tools – buy and manage US/CA numbers and attach them to agents
• SMS + voice workflows – send texts, view conversations, place calls, and inspect transcripts
• Agent configuration – create agents with voices, system prompts, call transfer, voicemail, and tuning options
• Webhooks + usage tools – configure inbound events and check plan limits, call/message volume, and breakdowns

It’s open-source (MIT license).

Link in the reply 👇

[Dami’ Adenuga @DAMIADENUGA]

Avoid this mistake for your own safety ⚠️

[Kalshi Finance @Kalshi_Finance]

JUST IN: The Magnificent 7 has fallen to its cheapest valuation relative to the S&amp;P 500 in more than 10 years

[Glenn Tunes @glenn_tunes]

JUST SO I UNDERSTAND THIS, BLOCKING THE STRAIT OF HORMUZ IS UNFAIR, BUT BLOCKING OIL SHIPMENTS TO CUBA IN ORDER TO COLLAPSE THEIR WHOLE COUNTRY, IS FAIR 🤔 DID I GET THAT RIGHT 🙄

[Morris Monye @Morris_Monye]

So if Alex Onyia didn’t decide to take these kids to Rome, you mean the world would not have seen us win gold?

Some other country would have won and we would have thought they were the brightest on earth?

Bad Governance is hiding the greatness of Nigerians.

I’ve said on previous tweets that Nigerians are the brightest and smartness people on earth. No enabling environment to showcase that brilliance.

[ParodyNews @ParodyNewsnz]

@flahenriquebr The longer version with subtitles.

[FLA Henrique @flahenriquebr]

Fizeram um compilado de 4 minutos mostrando os lances em que a Argentina foi favorecida contra o Egito.

Simplesmente um escândalo mundial. Quanta sujeira envolvida. 🤢

[Omojo @Omojotrades]

The fascinating thing about this Cape verdes run in the world cup is that they played against three world champions and didn't lose a single game in 90 minutes

[B @utdbrxy]

Cape Verde went to war with Spain, Uruguay and Argentina in their first World Cup. We will make sure history remembers this run

[SHACK @ShackShackou]

@StealthyM00S3 “Nothing about him is French” except his French nationality, his French-Algerian mother, France U18, France U21, France Olympic team, and France senior team.

He never represented England. You’re not defending football logic, you’re just crying because he chose better.