Jeff Scott

9.1K posts

Jeff Scott banner
Jeff Scott

Jeff Scott

@JeffScottDev

Canadian, Husband, Father, Software Engineer. Life is one big party when you're still young. Can't be a fool, son, what about the long run?

Canada Katılım Temmuz 2009
397 Takip Edilen826 Takipçiler
Jeff Scott
Jeff Scott@JeffScottDev·
@minchoi This might be the most unimpressive thing I have seen in a long time. Would have been cool 10 years ago maybe. Wheels? C'mon.
English
0
0
1
55
Min Choi
Min Choi@minchoi·
Robots are getting scary... Toyota just unveiled CUE7. This AI robot can now dribble, move, and shoot free throws. 💀
English
620
1K
5.9K
620.4K
DogeDesigner
DogeDesigner@cb_doge·
Grok 4.20 Reasoning just took the #1 spot on the BridgeBench reasoning benchmark. 🔥 Beating GPT-5.4, Claude Opus 4.6, Google Gemini and others. Week after week, Grok keeps climbing across benchmarks. 🚀
English
337
288
1.5K
9M
ELEKTRA
ELEKTRA@RealElektra·
I only use Grok. My life has had such an upgrade since Grok’s arrival! Nowadays I even teach others how to use it - and they are surprised how much you can do with it. Yet, I am baffled that esp. academia doesn’t switch to Grok. Personally, I refuse to downgrade to other AIs. For that’s how I experience it - as a downgrade. Perhaps an idea to make colleges an offer they cannot refuse?
English
1
0
2
573
Zac
Zac@PerceptualPeak·
I hate to be yet another voice in the sea of complaints regarding the quality of Opus lately but.....I've legitimately noticed a palpable degradation in performance. It's extremely frustrating.
English
8
6
65
1.5K
Jeff Scott
Jeff Scott@JeffScottDev·
POV when Claude Code is down.
GIF
English
0
0
0
223
Victor M
Victor M@victormustar·
@realsanb I would say around 5 hours but idk I was mostly doing other things during inference
English
2
0
1
1.2K
Victor M
Victor M@victormustar·
GLM-5.1 > Claude Code (Opus 4.6)? I'm tripping or CC has become very bad but built a Three.js racing game to eval and it's extremely impressive. Thoughts: - One-shot car physics with real drift mechanics (this is hard) - My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen - 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters - All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio! - Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed You are going to hear about this model a lot in the next months - open source let's go 🚀🚀
English
70
102
1.3K
180K
Jeff Scott
Jeff Scott@JeffScottDev·
We just all need to realize that Enterprise customers are paying @AnthropicAI MUCH more money than we are; with built in profit margins. Unfortunately I don't think they have any motivation to make our experience as developers any better, nor do they care if a percentage of us leave. If I were to guess they are actually trying to drive attrition from the power users that are costing them money each month off the Max plans.
English
0
0
0
9
Hey Jay
Hey Jay@JJeffrey100·
@CanadianDevDad @heygeorgekal @claudeai I did this last week. Sonnet got me to 3 hours on 20x vs. 1 hour on opus. BUT, they also have a sonnet only limit, which I hit for the week by Wednesday, so they forced me back to Opus 👎
English
1
0
0
54
George Kal
George Kal@heygeorgekal·
Been a @claudeai fanboy for a long time but the usage limits even on claude max are getting ridiculous Paying for both 100 claude and 100 codex this month. The difference is night and day. - Codex ($100): running parallel agents, barely touching the limits - Claude ($100): 3-4 deep prompts and i'm locked out I get it, they're probably focused on enterprise, but if you're charging $100/mo and people hit the wall after 30 minutes, they will churn. The product is incredible. The packaging is not.
English
56
7
230
21.4K
Jeff Scott
Jeff Scott@JeffScottDev·
@heygeorgekal @claudeai Unfortunately my Claude sub renewed just last week so i'm stuck here for a few weeks but then yes, I'm going to Codex. What harness are you using?
English
1
0
0
120
Gavin Purcell
Gavin Purcell@gavinpurcell·
@TheStalwart anecdotally, opus is doing things that i want it to do this am that it couldn't seem to do yesterday
English
2
2
16
13.8K
Jeff Scott
Jeff Scott@JeffScottDev·
@bridgemindai It's like going back in time to early last year with the quality of implementations.
English
0
0
1
198
BridgeMind
BridgeMind@bridgemindai·
CLAUDE OPUS 4.6 IS NERFED. BridgeBench just proved it. Last week Claude Opus 4.6 ranked #2 on the Hallucination benchmark with an accuracy of 83.3%. Today Claude Opus 4.6 was retested and it fell to #10 on the leaderboard with an accuracy of only 68.3%. A 98% increase in hallucination. bridgebench.ai just confirmed that Claude Opus 4.6 has reduced reasoning levels and is nerfed.
BridgeMind tweet media
English
481
668
6.6K
980K
Uncle Bob Martin
Uncle Bob Martin@unclebobmartin·
@tmaiaroto I think the code will get cleaner, because it won't be humans writing it. Humans will, instead, be managing it. And it's easier to force someone else to be clean than it is to be clean yourself. ;-)
English
18
42
481
53.5K
Uncle Bob Martin
Uncle Bob Martin@unclebobmartin·
What we are losing with AI is syntax -- and good riddance. The less our brains are occupied by semicolons and braces the better. There are much more important things for us to consider and manage.
English
117
154
1.9K
241.9K
Kenton Varda
Kenton Varda@KentonVarda·
Since like 10 people have brought this up: I'm actually fine with there being maps, what I really don't want is for my location to be highlighted on the map. I want to have to figure it out from landmarks.
English
7
0
27
2.8K
Jeff Scott
Jeff Scott@JeffScottDev·
Released my fist native app ever (iOS & Android) Currently has 100 users and going strong. Thanks to @convex, @expo, @hero_ui which made the development of a cross platform app as painless as something could possibly be. Only up from here. gokanic.com
Jeff Scott tweet media
English
0
0
0
27