Chris Edwards (@ChrisEdwards357) profile picture

Follower of Christ, Husband, Father, AI Enthusiast

Ohio
Joined May 2008
Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)Photo by Chris Edwards (@ChrisEdwards357)
Chris Edwards retweeted
Imagine telling someone in 1950 that one day every person on Earth would carry a device that could answer any question, in any language, and patiently explain it until they understood. Then imagine telling them people would be angry about it.
56
138
8
1,226
19,061
Chris Edwards retweeted
Elon Musk has contributed more to human progress than every politician who has spent their time harassing him combined. It's not even close.
1,845
8,398
340
85,275
885,559
Chris Edwards retweeted
The EU should be abolished and sovereignty returned to individual countries, so that governments can better represent their people
28,659
46,362
6,509
274,716
40,100,318
What happened to OpenAI? Anthropic released Opus 5.5, an amazing model, and its been crickets from OpenAI. Now Fable 5.2, and still nothing from OpenAI?
1
23
Chris Edwards retweeted
It's absolutely wild how a single X post can erase $3 trillion from the US stock market.
144
214
25
2,114
72,128
Let the Claude Code UI clutter begin! So I saw this unexpected clutter in my Claude Code UI this morning. I hope plugins don't start cluttering my UI like this. I uninstalled for now. (Good plugin...but not worth my screen real-estate)
2
59
I tried to get my factory to design good abstractions for the code it writes. However I am finding that abstraction locks in the assumptions that motivated it. When that assumption changes, or if the AI got it wrong (it will), the abstraction is much harder to change.
2
3
161
I think the bottom line is, to write good abstractions, you need to be able to PREDICT the shape of future problems the system has to solve. They have to fit the shape of the abstraction. AI doesn't have the context to predict this.
1
10
It has been said, "A bad abstraction is worse than no abstraction at all." Abstractions should be used only for things you know are not going to change. The AI does't have this foreknowledge, so it's poor at predicting useful abstractions that last. This changes my thinking.
31
When intelligence is "good enough" in open/cheap models (which is just about here), there will be a huge drop in the demand for frontier models. I already have MUCH less need for them.
47
This is a great article. Sounds advice for these uncertain times.
Your job may be surviving on inertia. Your resentment won’t extend the runway. What do you actually want to do with the intelligence now at your disposal?
1
48
Chris Edwards retweeted
Now do .agents
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.
13
10
450
33,860
Chris Edwards retweeted
Great moral modeling for open source too.
57
94
9
1,240
70,159
I absolutely hate 5-hour limits. It destroys mental health by dragging work outside normal hours just to "use" what you paid for. This is not healthy for us humans.
2
57
I just love that Claude is erroring out with 500s left and right and the Anthropic status page says "No incidents reported today". Total BS.
2
58
I think agent memory is a great idea. But it makes it hard to do harness engineering if you work on a team. Does the agent work well because of the harness or your memories? You want a consistent harness, but everyone's memories differ. It's the modern "Works on my box!"
1
4
120
When code reviewing, I have seen Sonnet 5 on high use so many tokens it costs more than Opus, and finds fewer issues. I guess it just doesn't know when to stop.
1
3
87
If planning with a smart model, don't let it be too prescriptive and detailed about the implementation. Otherwise the agent that implements it may follow the details even when it finds they are wrong. No plan survives contact with the code. Leave flexibility for the implementer.
1
2
61
I have found it helps to specify the why clearly in the plan. Then tell the implementer to "do the right thing". I found slop from sol, and asked why, and it said, "I did it because the plan said I had to." Explaining why and empowering the implementer seems to fix this.
2
31
I'm really getting frustrated with the way Claude Code has been hiding all the tool calls it makes. It's so hard to tell if it's stuck or still calling tools. This grouping of all calls under one aggregate heading is not the way!
56