Results
250 articlesSort
13:59EN
Matthew Berman· Apr 5, 2024SWE-agent Tutorial: Navigating Repositories and Attempting GitHub FixesMatthew Berman, Carlos · Forward FutureMatthew Berman sets up a research coding agent, hits an installation problem and a cost limit, then shows an author’s successful SymPy benchmark example.
14:23ENMatthew Berman· Mar 31, 2024Testing DBRX: Coding Strengths and Reasoning GapsMatthew Berman · Forward FutureMatthew Berman examines Databricks’ open-weight model and puts it through coding, arithmetic and reasoning prompts.
14:58ENMatthew Berman· Mar 30, 2024OpenDevin’s Early Coding Agent: A 2024 Installation and DemoMatthew Berman · Forward FutureMatthew Berman installs an early open-source coding-agent project and tries a calculator and a simple web page, while encountering setup and browser issues.
1:10:33EN
20VC with Harry Stebbings· Mar 20, 2024Podcast · 2 speakersJean-Michel Lemieux on Shipping, Hiring and Product AlignmentGuest Jean-Michel Lemieux · Host Harry StebbingsThe former Shopify CTO and Atlassian engineering leader explains how he balances speed and quality, aligns decisions and builds teams.
19:51ENMatthew Berman· Mar 15, 2024Devin’s 2024 Launch: Coding-Agent Demos and Benchmark ClaimsMatthew Berman, Scott Wu, Neal, Walden · Forward FutureMatthew Berman examines Cognition’s software-agent demonstrations, interface and SWE-bench comparison alongside earlier coding projects.
3:30EN
Jane Street· Mar 13, 2024Richard Eisenberg on Jane Street's OCaml ExperimentsRichard Eisenberg · Jane StreetJane Street's compiler team is exploring unboxed types, locality modes, and data-race-free parallelism to make OCaml's performance and memory management better suited to its needs.
11:07ENJane Street· Feb 29, 2024How OCaml Locals Use a Separate StackRichard Eisenberg · Jane StreetA list example shows how region-scoped local values can avoid repeated garbage-collected allocations.
55:29ENMatthew Berman· Feb 24, 2024Building a CrewAI Newsletter Team: Scraping, Summarizing and DebuggingMatthew Berman, Joe · Forward FutureMatthew Berman builds a two-agent newsletter prototype, works through input and scraping errors, and shows what still needs to be fixed.
23:25ENJane Street· Feb 20, 2024Richard Eisenberg: How OCaml Locals Reduce Garbage-Collected AllocationRichard Eisenberg · Jane StreetAn annotated list-processing example shows why locality must be preserved both when values are created and when functions consume them.
22:27ENJane Street· Feb 7, 2024How OCaml Infers LocalityRichard Eisenberg · Jane StreetA look at local and global mode inference, module signatures, mode crossing for integers, and conversions between function types.
15:17ENJane Street· Jan 31, 2024OCaml Locals, Modes, and SubmodingRichard Eisenberg · Jane StreetA worked explanation of how local and global modes control escaping values, and how those modes interact with function types.
9:25ENMatthew Berman· Jan 31, 2024Matthew Berman Tests Meta’s Code Llama 70B on a Snake GameMatthew Berman · Forward FutureA 2024 look at Meta’s coding-model release, a SQL-focused fine-tune and a hands-on test that did not work on the first attempt.
7:20ENMatthew Berman· Jan 30, 2024Using Cody and Ollama for Local Code CompletionMatthew Berman · Forward FutureIn a sponsored 2024 tutorial, Matthew Berman sets up Code Llama 7B for Cody autocomplete and demonstrates additional hosted coding features.
12:52ENJane Street· Jan 23, 2024OCaml Local Variables, Return Values and RegionsRichard Eisenberg · Jane StreetA worked example shows how `local_` and `exclave_` let a function accept a local value and return a local structure in its caller's region.
46:36EN
No Priors: AI, Machine Learning, Tech, & Startups· Jan 18, 2024Podcast · 2 speakersAfter a decade of code search, Sourcegraph’s CTO says the coding-AI fight is outside the modelHost Sarah Guo, Elad GilBeyang Liu on Cody, why keyword search still does most of RAG, and why CS fundamentals get more valuable as AI compresses the middleware.
8:52ENJane Street· Jan 5, 2024Introducing Local Parameters in OCamlRichard Eisenberg · Jane StreetA demonstration of how Jane Street's experimental local mode restricts escaping values and makes function interfaces easier to reason about.
24:54ENMatthew Berman· Dec 22, 2023Matthew Berman's 2023 Prediction for AI and the Future of ProgrammingMatthew Berman, Matt Welsh, McKay Wrigley · Forward FutureBerman argues that natural-language interfaces and AI agents could transform software development, while acknowledging the limits of coding tools and his uncertain timeline.
17:08ENMatthew Berman· Dec 21, 2023Building and Testing a Login App With GPT PilotMatthew Berman · Forward FutureMatthew Berman demonstrates the 2023 VS Code workflow for AI-assisted planning, coding and debugging an authentication prototype.
55:34ENJane Street· Nov 29, 2023Andrew Hunter on Performance Engineering for Low-Latency SystemsYaron Minsky, Andrew Hunter · Jane StreetWhy small optimizations pay at hyperscale, why trading latency is harder to measure, and how profiling, tracing, language design and hardware fit together.
10:37ENMatthew Berman· Nov 17, 2023Testing DeepSeek Coder on Forms, Bugs and a Snake GameMatthew Berman · Forward FutureMatthew Berman puts the 2023 coding model through a small hands-on rubric, from JSON and unit tests to a playable game.
15:03ENMatthew Berman· Oct 10, 2023A 2023 AutoGen Tutorial: Local Agent Setup and Code ExecutionMatthew Berman · Forward FutureMatthew Berman builds a local assistant and user-proxy workflow, then tests how the agents generate and run Python. AutoGen’s packages and APIs have changed since this tutorial.
7:32ENMatthew Berman· Oct 4, 2023MageGPT Generates a Wasp To-Do App: A 2023 DemonstrationMatthew Berman · Forward FutureMatthew Berman uses a Wasp-sponsored app generator to build, run and deploy a basic full-stack to-do app.
29:38ENNo Priors: AI, Machine Learning, Tech, & Startups· Sep 21, 2023Podcast · 2 speakersA Beginner Just Shipped a $250K Business. Professionals Got 30 Percent.Host Sarah Guo, Elad GilReplit CEO Amjad Masad on Ghostwriter, why a 3-billion-parameter model was enough, and the agents he wants earning bounties while you sleep.
10:20ENMatthew Berman· Aug 30, 2023Phind Code Llama 34B vs GPT-4: A 2023 Python Coding TestMatthew Berman · Forward FutureMatthew Berman compares a quantized Phind fine-tune with GPT-4 on games, short functions and refactoring, with mixed results.Load moreShowing 24 of 250