TIM (@timalive) header
TIM (@timalive) profile picture

Tim Vieyra. Springbok Rugby, Tech and Archeology

Cape Town
Joined October 2008
Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)Photo by TIM (@timalive)
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.
2,554
7,298
2,906
55,180
17,120,281
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!
41
132
6
757
66,671
Genius move, do things that bring people to you. Everyone wants a third space.
Thinking spaces, coming to a city near you. Good vibes. Great hats. Slop free.
1
1
149
5,826
Half of the value I add as CEO is just applying urgency to situations
154
276
46
5,405
341,048
Replying to @Rainmaker1973
Its almost like it was designed by a benevolent creator 🤔
6
1
269
3,759
Replying to @sfliberty
You cannot be all three: 1. A thinking person 2. A person who cares for the poor 3. A hater of free markets
1
3
136
What does Apples lack of focus on AI at #WWDC25 show? Critics will say that they are far behind the shift in tech. Ive’s partnership with @OpenAI signals that perhaps the battle for how to usefully and reliably use the inventive technology is just starting.
1
1
1
114
After Perplexity Labs, I would say probably 98-99%.
101
355
43
3,619
306,243
Lockdown life lessons 😂😂😂 #LockieDownMyNou
Happy Friday everyone.
1
1
94
Bulls at their best. Beat Bayonne 22-32 away. That's impressive in anyone's book. Off to Edinburgh next week ... 2nd stop of 4 on a 5 week tour!
4
2
60
3,090
Reminder: Tolkien hated Disney. He called them "hopelessly corrupted" and knew they'd ruin any story they touched. Why? Tolkien's storytelling philosophy was profoundly different… (thread) 🧵
955
8,953
851
67,568
11,400,255
In the fall of 1972, President Nixon announced that "the rate of increase of inflation was decreasing". Probably the first time a sitting president used the 3rd derivative to increase the chances of reelection.
106
1,148
121
15,100
530,140
Replying to @rugby_ap
Swak swak swak
1
7
3,993
While cynical people may appear more intelligent, they perform less well in cognitive tests.
21
18
4
356
51,581
An all-time great 🇿🇦 Pieter-Steph Du Toit is the 2024 Men's 15s Player of the Year #WorldRugbyAwards
239
2,212
392
12,589
572,505
Dear son,
344
26,924
646
195,960
12,162,099
Love. Joy. Peace. Patience. Kindness. Goodness. Faithfulness. Gentleness. Self Control.
526
1,673
139
14,585
Many such cases.
Replying to @xenocosmography
... There's something perfect about Google's founding 'Don't be evil' slogan btw. Moral conviction demonstrably has zero to strongly negative value. The most evil actors feel best about what they're doing.
14
9
2
179
55,692