TIM

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.

@flipvandermerwe @janetmachuka_ 🤣

@janetmachuka_ @timalive I told you #teamlenovo

Thinkpad team, please gather! This in INSANE😂😂

Wait, does this mean costco hotdogs were wildly overpriced in the 80s?!

@BlaBlaRahRah Yoh

@CaptSpringbok South africa has been there... chin up chaps.

Welsh rugby brothers and sisters - keep the faith. Your team will come good again. It may take time, but Wales is a proud rugby nation with a rich history and an incredible spirit. Keep going, you’ll find a way. Thanks for the game. 🇿🇦🤝🏴󠁧󠁢󠁷󠁬󠁳󠁿

The general take from SA rugby X

@tribe_talking Nope. We are all horrified. 🇿🇦

Saffa fans will say this is legal and its all a conspiracy

An astounding fact

Rassie playing 3d chess here #ssrugby @SSRugby @SuperSportTV

when starting something new, ask every day: how do I speed up the acquisition of information

@SawyerMerritt The argument for index funds holds up when they are a small proportion of the market (low cost, market know best) but falls apart at higher proportions (erodes the fundamental market mechanism - which is decisions based on skin in the game)

NEWS: The White House is considering new steps to limit the power of proxy advisers like Glass Lewis and ISS, as well as major index-fund managers — a move both Elon Musk and Jamie Dimon have publicly called for. Trump administration officials are discussing at least one executive that could include a broad ban on shareholder recommendations or an order blocking recommendations on companies that have engaged proxy advisers for consulting work. Officials also are exploring limits on how index-fund managers are allowed to vote, seeking to curtail the power of such behemoths as BlackRock, Vanguard Group and State Street. These three together own on behalf of clients roughly 30% or more of many of the biggest U.S. publicly traded companies. One measure being discussed would require these index-fund managers to mirror their votes in line with clients who choose to vote. This is would be great news if they implement this!

Everyone has within them a giant in need of a mission and a child in need of a hug

@eurofounder Strawman vs strawman

A founder of a SF-based startup asked why are we not using AI to code, or an app called Cursor (??) He said it writes code 10x faster than humans an everyone uses it in Silicon Valley I asked him: “but who reviews the code for compliance?” He looked confused and said “dude what we just ship it to prod” I started sweating from anger but calmed myself and explained that in Europe, we have a Software Quality Assurance Board that reviews every line of code before deployment He said that must “kill momentum” I said momentum without oversight kills startups, and promptly called California authorities to report unreviewed code deployment at the startup They asked me to stop calling them every day with “stupid shit” Silicon Valley is completely doomed

Super Sacha leads the Boks centurion celebrations for Siya keo.co.za/super-sacha-le…

Tampa knows gyms

@scrumming_ten A trip to ellis park is an ordeal. I say move to another ground outside the CBD

There is a school of thought that perhaps Ellis Park shouldn't get Springbok games until the JHB residents get off their backsides and start going to Lions games.

@birdabo But where would the notch go

startup idea: circular laptops.

Is it just me or is @claudeai Opus often long winded. Like the genius professor rambling on about intricacies of some or other fascinating subject.

At a AWS / Anthropic event in San Francisco. Excitement is tangible about what AI is unlocking.

@akshay_pachaar Assuming it would need to start with some kind of minimal viable model

Did Stanford just kill LLM fine-tuning? This new paper from Stanford, called Agentic Context Engineering (ACE), proves something wild: you can make models smarter without changing a single weight. Here's how it works: Instead of retraining the model, ACE evolves the context itself. The model writes its own prompt, reflects on what worked and what didn't, then rewrites it. Over and over. It becomes a self-improving system. Think of it like the model keeping a living notebook where every failure becomes a lesson and every success becomes a rule. The results are impressive: - 10.6% better than GPT-4-powered agents on AppWorld - 8.6% improvement on financial reasoning tasks - 86.9% lower cost and latency No labeled data required. Just feedback loops. Here's the counterintuitive part: Everyone's chasing short, clean prompts. ACE does the opposite. It builds dense, evolving playbooks that compound over time. Turns out LLMs don't need simplicity. They need context density. The question here is how to manage all this information and experience. This is where building a real-time memory layer for Agents (eg. @zep_ai ) can be a great solution and active area of research going forward. What are your thoughts? I have linked the paper in the next tweet! ____ If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️ For more insights and tutorials on LLMs, AI Agents, and Machine Learning!