TIM retweeted
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.
Super Sacha leads the Boks centurion celebrations for Siya keo.co.za/super-sacha-leads-…
TIM retweeted
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!
TIM retweeted
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
TIM retweeted
Lockdown life lessons 😂😂😂 #LockieDownMyNou
TIM retweeted
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!
TIM retweeted
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) 🧵
TIM retweeted
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.
TIM retweeted
While cynical people may appear more intelligent, they perform less well in cognitive tests.
TIM retweeted
An all-time great 🇿🇦
Pieter-Steph Du Toit is the 2024 Men's 15s Player of the Year
#WorldRugbyAwards
TIM retweeted
Love.
Joy.
Peace.
Patience.
Kindness.
Goodness.
Faithfulness.
Gentleness.
Self Control.
TIM retweeted
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.






























